HomeGemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior
Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma Scope 2.
Announcing Gemma Scope 2, a comprehensive, open suite of interpretability tools for the entire Gemma 3 family to accelerate AI safety research. This visual shows Gemma Scope 2 using sparse autoencoders and transcoders to show researchers how the model is determining a potential fraudulent email.
Disclaimer: This content has been automatically aggregated from GOOGLE DEEPMIND for informational purposes. To read the original article, please visit GOOGLE DEEPMIND.
