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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7448
    Prev
    Next
    INDEX
    Explanations

    information related to unisex bathrooms and their design characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    IsMutable
    -0.58
     AssemblyCulture
    -0.54
     ویکی‌پدیای
    -0.49
    UrlResolution
    -0.48
    eleste
    -0.48
    endphp
    -0.46
    Попис
    -0.46
    phosa
    -0.46
    TargetException
    -0.46
    ьаж
    -0.45
    POSITIVE LOGITS
     bath
    0.43
     shower
    0.42
    浴
    0.41
     bathroom
    0.40
     BIBSYS
    0.40
    bathing
    0.38
    shower
    0.38
     bathing
    0.37
    bathroom
    0.37
    RefNanny
    0.36
    Activations Density 0.004%

    No Known Activations