© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 5846
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their roles or actions within social or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.59
    __(/*!
    -0.51
    fillType
    -0.42
    internalType
    -0.39
     adjourn
    -0.39
    bindValue
    -0.39
    Espèce
    -0.37
    Drawn
    -0.36
    Defined
    -0.35
     AssemblyVersion
    -0.35
    POSITIVE LOGITS
     agreed
    1.17
     accepted
    0.99
     consented
    0.91
    agreed
    0.88
     Agreed
    0.77
     concurred
    0.71
     graciously
    0.69
    Agreed
    0.69
    accepted
    0.68
     approved
    0.65
    Activations Density 0.574%

    No Known Activations