© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5303
    Prev
    Next
    INDEX
    Explanations

    expressions related to health consequences or controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]));
    
    -0.90
     considérons
    -0.87
    }),
    
    -0.86
    }))
    
    -0.82
    }));
    
    -0.82
    ✨:
    -0.82
    ])):
    -0.82
    MLLoader
    -0.81
    сылкі
    -0.80
    новништво
    -0.80
    POSITIVE LOGITS
    0
    0.78
    1
    0.71
    2
    0.65
     Sal
    0.60
    żym
    0.57
     Ann
    0.53
    5
    0.53
    4
    0.53
    مار
    0.51
     Salv
    0.51
    Activations Density 0.157%

    No Known Activations