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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 130954
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web development and CSS frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    ScopeManager
    -0.68
    typeorm
    -0.58
    providedIn
    -0.55
     NavController
    -0.55
     StatelessWidget
    -0.54
    wapV
    -0.52
    exitRule
    -0.52
    KommentareTeilen
    -0.51
    MigrationBuilder
    -0.51
    存于互联网档案馆
    -0.50
    POSITIVE LOGITS
    uglify
    0.43
    //
    0.40
     desem
    0.39
     Lade
    0.39
     Sta
    0.39
     stacked
    0.38
     Bản
    0.38
    boot
    0.38
     Middle
    0.37
    Middle
    0.37
    Activations Density 0.075%

    No Known Activations