Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 58819
    Prev
    Next
    INDEX
    Explanations

    elements related to permissions and user roles

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

    sending from or filtering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repuesto
    -0.34
     viejos
    -0.34
     själva
    -0.33
     ingenieros
    -0.33
     refugiados
    -0.33
    แพ
    -0.32
     abogados
    -0.32
    shared
    -0.32
     pilote
    -0.32
    ชั้น
    -0.32
    POSITIVE LOGITS
    msgSender
    0.79
    featureID
    0.63
    complexContent
    0.62
    migrationBuilder
    0.62
    HandlerContext
    0.61
    Reentrant
    0.59
    oa̍t
    0.58
     onlyOwner
    0.57
    DataAnnotations
    0.56
     يتيمه
    0.56
    Activations Density 0.001%

    No Known Activations