Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92732
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in testimony or legal proceedings

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

    Mrs. and Duchess titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    offerta
    -0.41
    MigrationBuilder
    -0.38
     unieke
    -0.37
     cometido
    -0.36
    obiettivo
    -0.36
    boa
    -0.34
     Weber
    -0.34
     pozycji
    -0.34
     yoksa
    -0.33
    effetto
    -0.33
    POSITIVE LOGITS
    IUrlHelper
    0.71
    ISupport
    0.66
    ArgsConstructor
    0.63
    DockStyle
    0.59
    MessageTagHelper
    0.57
    MLLoader
    0.56
     CURIAM
    0.56
    Aktualisiert
    0.55
     contextLoads
    0.53
    UrlResolution
    0.52
    Activations Density 0.005%

    No Known Activations