© 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. 13698
    Prev
    Next
    INDEX
    Explanations

    words and terms related to programming libraries and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    kafka, glut, ionic, cstdio, plugins

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.52
    Alas
    -0.35
     DEAD
    -0.31
    bull
    -0.31
    dead
    -0.31
    complex
    -0.31
     Gör
    -0.30
    oretical
    -0.29
     Taschen
    -0.29
    nehmer
    -0.29
    POSITIVE LOGITS
     resourceCulture
    1.87
     AssemblyCulture
    1.57
    kafka
    1.34
    prefixer
    1.05
    cstdio
    0.92
    FormBuilder
    0.84
    HasAnnotation
    0.82
    WireFormatLite
    0.77
    InjectAttribute
    0.74
     chi̍t
    0.72
    Activations Density 0.000%

    No Known Activations