© 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. 5280
    Prev
    Next
    INDEX
    Explanations

    occurrences of bracketed or enclosed terms and their context within a document

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

    parentheses and quoted words/phrases

    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
    WebpackPlugin
    -0.39
     initComponents
    -0.38
    éroport
    -0.36
    harapkan
    -0.34
    testens
    -0.34
    StructEnd
    -0.34
    paravant
    -0.33
    addGap
    -0.32
    brtc
    -0.31
     paraître
    -0.31
    POSITIVE LOGITS
    CodeAttribute
    0.55
    httphttps
    0.54
     ***!
    0.53
    Vidite
    0.50
    下载附件
    0.49
     otomatig
    0.49
     BoxFit
    0.46
     виправивши
    0.46
    LookAnd
    0.45
    aarrggbb
    0.44
    Activations Density 0.021%

    No Known Activations