© 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. 8736
    Prev
    Next
    INDEX
    Explanations

    instances of opening and closing braces commonly used in programming code

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

    private methods and constructors

    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
    P
    -0.23
    ta
    -0.22
     last
    -0.22
    var
    -0.22
     instance
    -0.22
     nær
    -0.22
    #
    -0.21
    <?
    -0.21
    DATABASES
    -0.21
     Wind
    -0.20
    POSITIVE LOGITS
     zwiſchen
    0.88
     fashiola
    0.87
    __':
    0.83
    __":
    0.82
    <unused28>
    0.82
    <unused80>
    0.82
    RegressionTest
    0.82
    <unused52>
    0.82
    [@BOS@]
    0.82
    <unused47>
    0.82
    Activations Density 0.008%

    No Known Activations