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. 70677
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
    ValueStyle
    -0.86
     propOrder
    -0.77
    reportWebVitals
    -0.77
    sizeCache
    -0.73
    səhifə
    -0.72
    addPreferredGap
    -0.71
    addGap
    -0.70
    IsMutable
    -0.68
    GraphicsUnit
    -0.67
    ſammen
    -0.67
    POSITIVE LOGITS
     costumbre
    0.38
     colgante
    0.37
     inglesa
    0.34
     maleta
    0.34
    ējās
    0.33
    interopRequire
    0.33
     découverte
    0.31
     almohada
    0.31
     zijne
    0.31
     sonriente
    0.31
    Activations Density 0.000%

    No Known Activations