© 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. 28-GEMMASCOPE-RES-16K
    11. 1075
    Prev
    Next
    INDEX
    Explanations

    code block structures or groupings in programming language syntax

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

    Code-related terms

    np_acts-logits-general · gemini-2.0-flash

    programming keywords and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     للاسماء
    -1.13
     nahilalakip
    -0.91
    featureID
    -0.90
    parsedMessage
    -0.88
     kaarangay
    -0.84
     Chwiliwch
    -0.82
     الحره
    -0.81
    principalColumn
    -0.77
     فريبيس
    -0.74
    Tikang
    -0.74
    POSITIVE LOGITS
    ook
    0.37
    assert
    0.34
    ↵
    0.32
    present
    0.30
     Técnico
    0.29
     présente
    0.28
     çıkar
    0.28
    $\
    0.27
    if
    0.27
    Julia
    0.27
    Activations Density 0.135%

    No Known Activations