© 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. 20-GEMMASCOPE-RES-131K
    11. 5118
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and syntax elements

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     betweenstory
    -0.74
    RegressionTest
    -0.57
     ]}
    -0.52
    SuppressLint
    -0.49
    ScopeManager
    -0.48
    onActivityResult
    -0.48
     متعلقه
    -0.47
    argout
    -0.46
    transQ
    -0.44
     AssemblyCompany
    -0.44
    POSITIVE LOGITS
    WritableDatabase
    0.49
     Bia
    0.43
    StructEnd
    0.40
     circular
    0.40
     bia
    0.40
    CPtr
    0.39
     cr
    0.39
     Horowitz
    0.39
     semi
    0.39
    出版年
    0.38
    Activations Density 0.003%

    No Known Activations