© 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. 93954
    Prev
    Next
    INDEX
    Explanations

    patterns related to the structure and functionality of code, particularly method definitions and their parameters

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

    programming code

    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
     simplifié
    -0.46
     EconPapers
    -0.43
    CloseOperation
    -0.43
    艋
    -0.42
    DoubleQuotes
    -0.41
     ویکی‌پدی
    -0.41
    Geplaatst
    -0.39
    findpost
    -0.38
    complexType
    -0.38
    Бахар
    -0.37
    POSITIVE LOGITS
     Whigs
    0.48
    
    0.47
    enheim
    0.46
    ioutil
    0.46
    +#+
    0.45
     avoient
    0.45
    ulipas
    0.45
     élas
    0.44
     myſelf
    0.44
     cuenca
    0.44
    Activations Density 0.019%

    No Known Activations