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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24545
    Prev
    Next
    INDEX
    Explanations

    references to seasonal celebrations and festivities

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

    Empty delimiter tags that mark transitions between section headings and their subsequent content paragraphs in formatted documents.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    DockStyle
    -0.53
    Tikang
    -0.52
    OGND
    -0.52
    Бахар
    -0.52
     &___
    -0.51
     HttpNotFound
    -0.47
    новниш
    -0.47
    featureID
    -0.46
    principalColumn
    -0.46
    webElementGuid
    -0.46
    POSITIVE LOGITS
    whose
    0.38
    endroit
    0.38
    pośred
    0.37
    setVerticalGroup
    0.37
     éditoriale
    0.37
     fermés
    0.36
     originalmente
    0.36
     Cardinale
    0.36
     voyez
    0.36
     spokesperson
    0.36
    Activations Density 0.022%

    No Known Activations