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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 62
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities

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

    French chat/conversation language patterns and punctuation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Hauptartikel
    -0.69
    ValueStyle
    -0.55
     Wikimedijinoj
    -0.53
     Administrativna
    -0.52
     ModelRenderer
    -0.49
     CanadaChoose
    -0.48
    SourceChecksum
    -0.48
    NoteOnEvent
    -0.45
     matchups
    -0.42
    abı
    -0.41
    POSITIVE LOGITS
    InstrumentedTest
    0.55
     certified
    0.41
    AnimationsModule
    0.40
     CURIAM
    0.39
    CloseOperation
    0.37
    RotationOrder
    0.36
    RuleContext
    0.35
    Климат
    0.35
     official
    0.34
    fassung
    0.33
    Activations Density 0.023%

    No Known Activations