© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8795
    Prev
    Next
    INDEX
    Explanations

    patterns or syntax related to coding or programming language structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiko
    -0.63
     Turquie
    -0.59
     Jenderal
    -0.57
     Internasional
    -0.57
     aikaa
    -0.55
     grecque
    -0.54
     Kerajaan
    -0.54
     Lingkungan
    -0.53
     Suomessa
    -0.53
     Grèce
    -0.52
    POSITIVE LOGITS
    󠁢
    0.84
     rowspan
    0.78
    begin
    0.77
    ’
    0.77
     colspan
    0.77
     FontWeight
    0.77
    mathrm
    0.77
    <tbody>
    0.74
    mml
    0.71
    󠁣
    0.69
    Activations Density 0.249%

    No Known Activations