© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    elements related to coding or programming syntax

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     sutures
    -0.39
    UserScript
    -0.37
    ########.
    -0.36
    mikro
    -0.36
     الرياضيه
    -0.36
     Lambda
    -0.35
     galle
    -0.34
     temples
    -0.33
     Roskov
    -0.33
     aph
    -0.33
    POSITIVE LOGITS
    новништво
    0.60
    MigrationBuilder
    0.56
    OGND
    0.55
     beide
    0.52
     BoxFit
    0.50
     båda
    0.50
     Beide
    0.49
     betrekking
    0.48
     ambos
    0.48
    aarrggbb
    0.48
    Activations Density 0.840%

    No Known Activations