Google DeepMind drops Gemma Scope 2 to peer inside Gemma 3's brain
Google DeepMind just open-sourced Gemma Scope 2, an interpretability suite designed to reverse-engineer how the Gemma 3 family actually thinks. Spanning models from 270M to 27B parameters, it uses sparse autoencoders and transcoders across every layer to map internal computations. Why it matters: It gives the safety community an open, microscopic look into why models hallucinate, get jailbroken, or disguise their reasoning.