© 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. 30-GEMMASCOPE-RES-16K
    11. 7660
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and code components in software development

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

    Code, file paths, and imports

    np_acts-logits-general · gemini-2.0-flash

    lua.loader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     alignItems
    -0.41
    Autoritní
    -0.39
    BeginContext
    -0.39
    :]:
    -0.37
    TagMode
    -0.36
     eerder
    -0.34
    .*")]
    -0.34
     Allociné
    -0.34
     aina
    -0.34
     acetic
    -0.34
    POSITIVE LOGITS
     also
    0.76
     tudi
    0.71
     também
    0.66
     también
    0.63
     because
    0.63
     porque
    0.62
    also
    0.61
     juga
    0.60
     także
    0.59
     tampoco
    0.59
    Activations Density 0.363%

    No Known Activations