© 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 EvalsExportsinterp-engineNEWAPI 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. 82905
    Prev
    Next
    INDEX
    Explanations

    numerical references and values related to data or statistics

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

    LaTeX document structure

    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
    сылкі
    -0.90
     الرياضيه
    -0.82
     resourceCulture
    -0.82
    parsedMessage
    -0.77
     ModelExpression
    -0.75
     témoig
    -0.74
    iſche
    -0.73
    isContained
    -0.73
     deſſen
    -0.72
    ьаж
    -0.72
    POSITIVE LOGITS
    documentclass
    0.36
     […]
    0.23
     ponsel
    0.22
    [
    0.22
     Considering
    0.22
     dieci
    0.22
     dez
    0.21
     diante
    0.21
     
    0.21
    rigado
    0.21
    Activations Density 0.004%

    No Known Activations