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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1806
    Prev
    Next
    INDEX
    Explanations

    programming terms related to document and UI management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.56
    isEmail
    -0.56
    id
    -0.52
    era
    -0.51
    이
    -0.50
    白
    -0.48
     HttpResponse
    -0.47
     trans
    -0.47
    ic
    -0.46
     sun
    -0.46
    POSITIVE LOGITS
    addPreferredGap
    5.22
    AccessorTable
    1.29
     disambiguazione
    1.13
    CloseOperation
    1.12
    addContainerGap
    1.08
     cherchés
    0.98
    awtextra
    0.98
     שוליים
    0.94
    Tikang
    0.93
    ValueStyle
    0.92
    Activations Density 0.001%

    No Known Activations