© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 83839
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and mathematical literature

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

    academic journals and periodicals

    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
    تقاوى
    -0.70
    EDEFAULT
    -0.62
     autorytatywna
    -0.62
     GoogleFonts
    -0.60
    XmlAccessType
    -0.59
    хьтан
    -0.59
    GraphicsUnit
    -0.57
     ब्रेकडाउन
    -0.56
    bitField
    -0.55
    tagHelperRunner
    -0.55
    POSITIVE LOGITS
     journals
    0.44
     journal
    0.42
     Journal
    0.40
     Quarterly
    0.35
    ownerId
    0.34
     bowls
    0.33
     Journals
    0.33
     समीक्षाएं
    0.32
     quarterly
    0.31
    GEBURTSDATUM
    0.30
    Activations Density 0.206%

    No Known Activations