© 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. 42680
    Prev
    Next
    INDEX
    Explanations

    programming constructs or statements in code

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

    build followed by closing parenthesis

    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
    AddTagHelper
    -0.96
    ChildScrollView
    -0.91
    DockStyle
    -0.91
     パンチラ
    -0.87
    <unused43>
    -0.84
    <unused17>
    -0.84
    <unused28>
    -0.84
    <unused16>
    -0.84
    <unused8>
    -0.84
    <unused14>
    -0.84
    POSITIVE LOGITS
     i
    0.25
    .
    0.25
     directamente
    0.25
    1
    0.24
     Meanwhile
    0.24
    2
    0.24
    (
    0.23
    –
    0.23
    3
    0.23
     lhes
    0.23
    Activations Density 0.012%

    No Known Activations