© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2491
    Prev
    Next
    INDEX
    Explanations

    syntactical and formatting elements in code or structured data

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

    Code, URLs, and file paths

    np_acts-logits-general · gemini-2.0-flash

    code comments and special characters

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Schatz
    -0.57
    -
    -0.56
    ://
    -0.52
     Zweig
    -0.52
    <h2>
    -0.49
    .
    -0.49
     Zug
    -0.47
     of
    -0.45
     about
    -0.45
     Bogen
    -0.44
    POSITIVE LOGITS
    parsedMessage
    0.94
    PerformLayout
    0.87
     disambiguazione
    0.86
    uxxxx
    0.80
    expandindo
    0.80
    contentLoaded
    0.79
    GraphicsUnit
    0.78
     iſt
    0.77
    __":
    0.76
    featureID
    0.75
    Activations Density 0.533%

    No Known Activations