© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1004
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and regulatory discussions or frameworks

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

    references to US research, technology, and policy.

    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
    AsUp
    -0.37
     razu
    -0.29
     übers
    -0.28
    Panamoan
    -0.28
     Италијани
    -0.27
     gröss
    -0.27
     rodilla
    -0.27
     antigüedad
    -0.26
     honlap
    -0.26
     presumably
    -0.26
    POSITIVE LOGITS
    ViewImports
    0.64
    ScopeManager
    0.64
    parsedMessage
    0.62
    httphttps
    0.62
     disponibilités
    0.59
     InputDecoration
    0.55
    AddTagHelper
    0.54
    devamını
    0.53
    GEBURTSDATUM
    0.52
     CanadaChoose
    0.50
    Activations Density 0.563%

    No Known Activations