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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73486
    Prev
    Next
    INDEX
    Explanations

    programming-related functions and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     république
    -0.43
    일본
    -0.42
    esgue
    -0.41
    COUVER
    -0.41
     assemble
    -0.40
    impanan
    -0.40
     scolaire
    -0.40
    gjenge
    -0.40
    böz
    -0.40
     jäsen
    -0.40
    POSITIVE LOGITS
    toFixed
    2.05
    ConfigureAwait
    0.69
    jspb
    0.55
    ResumeLayout
    0.51
    fix
    0.50
    Fix
    0.50
    defineProperty
    0.50
    fixed
    0.49
    FIXED
    0.49
     Fixes
    0.48
    Activations Density 0.003%

    No Known Activations