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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65591
    Prev
    Next
    INDEX
    Explanations

    references to investigations into various allegations or claims

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

    investigation into allegations

    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
     oprot
    -0.52
    AsUp
    -0.51
    SharedDtor
    -0.49
    ikyuu
    -0.48
    rawDesc
    -0.48
    сылкі
    -0.47
    참고
    -0.47
    abestanden
    -0.46
    KommentareTeilen
    -0.43
    queryInterface
    -0.43
    POSITIVE LOGITS
     allegations
    0.96
     alleged
    0.79
     allegation
    0.73
     suspected
    0.68
     whether
    0.68
     dugaan
    0.64
     accusations
    0.64
     why
    0.62
     complaints
    0.61
     possible
    0.60
    Activations Density 0.039%

    No Known Activations