© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 70878
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and legislative actions

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

    US House of Representatives, congressmen

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Senate
    -1.04
    Sen
    -0.98
     sen
    -0.96
     Sen
    -0.96
     senators
    -0.94
     senator
    -0.94
     Senator
    -0.93
    Senator
    -0.93
     Senators
    -0.91
     senate
    -0.91
    POSITIVE LOGITS
     congressman
    0.59
     Houſe
    0.57
     House
    0.56
    GEBURTSDATUM
    0.56
     house
    0.55
    Personensuche
    0.54
    KommentareTeilen
    0.52
     Congressman
    0.52
    House
    0.51
     HOUSE
    0.51
    Activations Density 0.056%

    No Known Activations