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

    Neuronpedia

    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. 78475
    Prev
    Next
    INDEX
    Explanations

    references to formal documents, citations, or structured elements like tables and mathematical lemmas

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

    labels followed by punctuation

    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
     keber
    -0.41
    webElementGuid
    -0.39
     nakalista
    -0.38
    __).
    -0.38
     Chat
    -0.36
    gpl
    -0.34
     getrennt
    -0.34
    guém
    -0.33
    talk
    -0.33
     Chances
    -0.33
    POSITIVE LOGITS
     CURIAM
    0.74
     resourceCulture
    0.66
    parsedMessage
    0.65
     wireType
    0.62
    StoreMessageInfo
    0.58
     &___
    0.57
    windowFixed
    0.57
    adaptiveStyles
    0.54
     Мексичка
    0.52
    migrationBuilder
    0.50
    Activations Density 0.047%

    No Known Activations