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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12787
    Prev
    Next
    INDEX
    Explanations

    HTTP request methods

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     للمعارف
    -0.69
     uLocal
    -0.67
    TypedDataSet
    -0.65
    GraphicsUnit
    -0.61
    VersionUID
    -0.60
     CURIAM
    -0.60
    RegressionTest
    -0.59
    findpost
    -0.59
    RetentionPolicy
    -0.59
    AlterField
    -0.59
    POSITIVE LOGITS
    RequestMethod
    0.69
    HttpMethod
    0.56
    httpMethod
    0.52
    zzleHttp
    0.41
    method
    0.36
     metodología
    0.35
    METHOD
    0.34
     RequestMethod
    0.32
    <!--[
    0.32
     HTTP
    0.32
    Activations Density 0.119%

    No Known Activations