© 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. 27-GEMMASCOPE-RES-16K
    11. 11985
    Prev
    Next
    INDEX
    Explanations

    references to authors and their contributions in academic or scholarly contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mystère
    -0.50
     humanidade
    -0.49
     doigt
    -0.49
     vœ
    -0.47
     onItemClick
    -0.46
     bł
    -0.46
     ennemi
    -0.45
     tromper
    -0.44
     ainfi
    -0.44
    basicConfig
    -0.44
    POSITIVE LOGITS
    oun
    0.77
    oup
    0.76
    ou
    0.73
    oute
    0.72
    cou
    0.71
    nout
    0.71
    oul
    0.71
     Bout
    0.70
    ouz
    0.68
     Rouse
    0.68
    Activations Density 0.588%

    No Known Activations