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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36701
    Prev
    Next
    INDEX
    Explanations

    semicolons and commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Glej
    -0.58
    InvalidProtocol
    -0.55
    nvarchar
    -0.54
    دانشنامهٔ
    -0.54
    ViewImports
    -0.54
    mappedBy
    -0.52
    invokeLater
    -0.52
    ysacchar
    -0.50
    hasMany
    -0.50
     שוליים
    -0.49
    POSITIVE LOGITS
     lenker
    0.63
    AndEndTag
    0.63
     propOrder
    0.57
    ьаж
    0.55
    évaluateur
    0.52
    getMenuInflater
    0.52
    ":[{
    0.52
    IContainer
    0.52
     McDaniel
    0.51
    Aholisi
    0.50
    Activations Density 0.015%

    No Known Activations