© 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. 21-GEMMASCOPE-RES-16K
    11. 10453
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and syntax elements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     يتيمه
    -0.88
     queſta
    -0.83
     kasarigan
    -0.77
    bootstrapcdn
    -0.76
    出版年
    -0.76
    Personensuche
    -0.72
    әрмәләр
    -0.71
    RectangleBorder
    -0.70
    writeField
    -0.69
    లాలు
    -0.69
    POSITIVE LOGITS
    UseVisualStyle
    0.36
    ↵↵
    0.36
     Once
    0.35
    .
    0.35
     however
    0.35
     However
    0.33
    Once
    0.32
     once
    0.31
     Again
    0.30
    However
    0.30
    Activations Density 0.772%

    No Known Activations