© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10748
    Prev
    Next
    INDEX
    Explanations

    technical terms related to image processing and filtering methods

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

    Filters or window sizes (e.g. 3, 5, 9)

    np_acts-logits-general · gemini-2.0-flash

    filter sizes like 5x5

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    ThroughAttribute
    -0.38
    skosten
    -0.35
     amargo
    -0.34
    föra
    -0.31
    }{*}{}
    -0.30
     dintre
    -0.30
    zyst
    -0.30
     rękaw
    -0.29
    principalTable
    -0.29
     separator
    -0.29
    POSITIVE LOGITS
    makeText
    0.61
    GTCX
    0.59
    ftagPool
    0.55
    tawesome
    0.52
    farwyddwr
    0.49
    blurRadius
    0.49
     neighbourhood
    0.48
    WithIOException
    0.48
    出版年
    0.48
    ectady
    0.48
    Activations Density 0.715%

    No Known Activations