© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 55002
    Prev
    Next
    INDEX
    Explanations

    phrases that reference stages or phases in various processes or developments

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

    stages of development or process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    blow
    -0.34
     ولد
    -0.32
     double
    -0.31
    版
    -0.30
     Bienen
    -0.30
     نهایت
    -0.29
    double
    -0.29
     bendera
    -0.28
     blow
    -0.28
    mail
    -0.27
    POSITIVE LOGITS
    CppMethod
    0.80
     estekak
    0.77
    DoubleQuotes
    0.76
    Stages
    0.75
    :✨
    0.74
    Phase
    0.70
     fase
    0.69
    SourceChecksum
    0.69
     Stages
    0.69
     intptr
    0.68
    Activations Density 0.146%

    No Known Activations