© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 121857
    Prev
    Next
    INDEX
    Explanations

    specific keywords or symbols related to programming and logical constructs

    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
    <em>
    -0.34
    GEN
    -0.32
    <h3>
    -0.30
    <b>
    -0.30
    τι
    -0.30
    相
    -0.30
    <i>
    -0.29
    인
    -0.29
    人
    -0.29
    #
    -0.29
    POSITIVE LOGITS
     MainAxisSize
    0.83
    ロウィン
    0.76
    IUrlHelper
    0.73
    HasForeignKey
    0.71
    Parcelize
    0.69
    StoryboardSegue
    0.69
     $_(
    0.69
    parsedMessage
    0.68
     مشين
    0.68
    exitRule
    0.67
    Activations Density 0.129%

    No Known Activations