© 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. 33-GEMMASCOPE-RES-16K
    11. 14719
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure in programming languages

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     StringTokenizer
    -0.66
    IsMutable
    -0.65
    TagMode
    -0.65
    writeFieldEnd
    -0.59
    #+#
    -0.59
    IVEREF
    -0.58
     виправивши
    -0.57
    EndContext
    -0.56
    endphp
    -0.56
    Aholisi
    -0.56
    POSITIVE LOGITS
     main
    1.61
    main
    1.47
    Main
    1.23
     MAIN
    1.21
     Main
    1.16
    MAIN
    1.15
    メイン
    0.88
     hlavní
    0.81
    主
    0.78
     hoved
    0.77
    Activations Density 0.218%

    No Known Activations