© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 8613
    Prev
    Next
    INDEX
    Explanations

    references to teams, players, and statistics in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    their stats and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Personendaten
    -0.71
    personal
    -0.65
     personal
    -0.62
    oa̍t
    -0.61
     فريبيس
    -0.58
    GIVEREF
    -0.57
    Personal
    -0.56
     Personal
    -0.56
    GOTREF
    -0.56
     personally
    -0.53
    POSITIVE LOGITS
    felves
    0.46
     blessés
    0.44
     offense
    0.42
     recent
    0.40
     histórica
    0.40
     exportaciones
    0.40
     récents
    0.39
     ultimi
    0.39
     economía
    0.39
     fortunes
    0.39
    Activations Density 0.019%

    No Known Activations