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. 84639
    Prev
    Next
    INDEX
    Explanations

    keywords related to support and assistance services, especially in contexts of safety and health care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ftagPool
    -0.50
    migrationBuilder
    -0.44
    errHandler
    -0.43
     становника
    -0.42
     dezelve
    -0.41
     zoude
    -0.40
    pushFollow
    -0.40
    Fernsehserie
    -0.39
    PerformLayout
    -0.39
     للمعارف
    -0.39
    POSITIVE LOGITS
     Autorizaciones
    0.45
     屋根
    0.43
    RegressionTest
    0.43
    InjectAttribute
    0.43
     Chwiliwch
    0.40
     rhestr
    0.40
    ChildScrollView
    0.39
     encima
    0.38
    Geplaatst
    0.38
    InitVars
    0.38
    Activations Density 0.057%

    No Known Activations