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. 80210
    Prev
    Next
    INDEX
    Explanations

    references to documentation and procedures related to emergency responses and equipment maintenance

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

    records and documentation history

    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
    Kariera
    -0.40
     motion
    -0.37
     NSFW
    -0.36
     scoring
    -0.36
     useDispatch
    -0.35
    DMETHOD
    -0.35
     capture
    -0.35
    tableFuture
    -0.35
     casting
    -0.34
    ollectionView
    -0.34
    POSITIVE LOGITS
    rungsseite
    0.68
    ScopeManager
    0.61
    GEBURTSDATUM
    0.52
     EconPapers
    0.46
     uživ
    0.45
    findpost
    0.45
    MigrationBuilder
    0.45
    rateful
    0.45
    AddTagHelper
    0.43
     Geheim
    0.42
    Activations Density 0.038%

    No Known Activations