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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 23912
    Prev
    Next
    INDEX
    Explanations

    questions related to governmental criteria and documentation

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

    whether fines imposed or reasons underlying

    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
     propOrder
    -0.54
    HtmlAttribute
    -0.52
     Signalez
    -0.50
     चीज़ों
    -0.48
    setVerticalGroup
    -0.47
    PerformLayout
    -0.45
     الحره
    -0.45
    bootstrapcdn
    -0.41
    UnusedPrivate
    -0.41
    出版年
    -0.41
    POSITIVE LOGITS
    EFIAPI
    0.43
     HttpNotFound
    0.42
    MigrationBuilder
    0.40
     administrative
    0.38
    有何
    0.37
    驶
    0.37
     nedenle
    0.37
    利益
    0.37
     operativa
    0.36
    ADMINISTR
    0.36
    Activations Density 0.029%

    No Known Activations