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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 21825
    Prev
    Next
    INDEX
    Explanations

    code related to module exports in JavaScript or TypeScript

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rev
    -0.40
    Enllaces
    -0.39
     public
    -0.39
     mess
    -0.38
    ⤹
    -0.38
     ports
    -0.37
     بلند
    -0.35
     HttpContext
    -0.35
    campos
    -0.35
    thée
    -0.35
    POSITIVE LOGITS
    verifyException
    0.59
     arquitetura
    0.55
    AddTagHelper
    0.55
     TestBed
    0.51
    webElementGuid
    0.46
    Personensuche
    0.45
    RefNanny
    0.45
     يتيمه
    0.45
    ViewImports
    0.44
    філь
    0.43
    Activations Density 0.000%

    No Known Activations