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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 12029
    Prev
    Next
    INDEX
    Explanations

    function declarations and invocations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]/
    -0.79
    )}_
    -0.78
    )');
    -0.77
    ')));
    -0.74
     Schild
    -0.72
    ingl
    -0.70
    Kurz
    -0.70
    getReal
    -0.69
     августа
    -0.69
     Harz
    -0.69
    POSITIVE LOGITS
    rillation
    0.95
     fibrillation
    0.82
    CORBA
    0.77
     Toussaint
    0.76
     Turner
    0.75
    ecycle
    0.74
     Baskets
    0.73
    querade
    0.73
    🔥🔥
    0.73
      
    0.72
    Activations Density 0.147%

    No Known Activations