© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3058
    Prev
    Next
    INDEX
    Explanations

    punctuation and syntactic elements in code snippets

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    programming language syntax elements and code structure patterns.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     للاسماء
    -0.88
    évaluateur
    -0.88
     ſind
    -0.86
     שוליים
    -0.79
    脚注の使い方
    -0.78
    contentLoaded
    -0.77
     esternos
    -0.76
     disambiguazione
    -0.75
    AndEndTag
    -0.74
     Audiodateien
    -0.73
    POSITIVE LOGITS
    ↵
    0.90
    ↵↵
    0.79
    ↵↵↵
    0.77
    ↵↵↵↵
    0.61
    ↵↵↵↵↵
    0.56
    ↵↵↵↵↵↵↵
    0.48
    ↵↵↵↵↵↵
    0.45
    <h2>
    0.41
    ↵↵↵↵↵↵↵↵↵
    0.41
    1
    0.41
    Activations Density 0.603%

    No Known Activations