New research analyzes the misuse of multimodal generative AI today, in order to help build safer and more responsible technologies.Read More
Gemma Scope: helping the safety community shed light on the inner workings of language models
Announcing a comprehensive, open suite of sparse autoencoders for language model interpretability.Read More
Gemma Scope: helping the safety community shed light on the inner workings of language models
Announcing a comprehensive, open suite of sparse autoencoders for language model interpretability.Read More
Gemma Scope: helping the safety community shed light on the inner workings of language models
Announcing a comprehensive, open suite of sparse autoencoders for language model interpretability.Read More
Gemma Scope: helping the safety community shed light on the inner workings of language models
Announcing a comprehensive, open suite of sparse autoencoders for language model interpretability.Read More
Gemma Scope: helping the safety community shed light on the inner workings of language models
Announcing a comprehensive, open suite of sparse autoencoders for language model interpretability.Read More
Gemma Scope: helping the safety community shed light on the inner workings of language models
Announcing a comprehensive, open suite of sparse autoencoders for language model interpretability.Read More
Gemma Scope: helping the safety community shed light on the inner workings of language models
Announcing a comprehensive, open suite of sparse autoencoders for language model interpretability.Read More
AI achieves silver-medal standard solving International Mathematical Olympiad problems
Breakthrough models AlphaProof and AlphaGeometry 2 solve advanced reasoning problems in mathematicsRead More
AI achieves silver-medal standard solving International Mathematical Olympiad problems
Breakthrough models AlphaProof and AlphaGeometry 2 solve advanced reasoning problems in mathematicsRead More