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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 24322
    Prev
    Next
    INDEX
    Explanations

    instances of data type definitions and parsing methods related to JSON in code

    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
    AddTagHelper
    -0.32
    ("*");
    -0.32
     Herkunft
    -0.29
    nestjs
    -0.29
     directamente
    -0.27
     simplesmente
    -0.27
     Grundlage
    -0.27
     Paglinawan
    -0.27
     vielmehr
    -0.27
    labor
    -0.26
    POSITIVE LOGITS
    новништво
    0.67
    脚注の使い方
    0.64
    MENAFN
    0.64
    MigrationBuilder
    0.64
    thenes
    0.59
    Derp
    0.59
     Infórmanos
    0.58
     ligiloj
    0.58
    PerformLayout
    0.57
    extAlignment
    0.57
    Activations Density 0.021%

    No Known Activations