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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1995
    Prev
    Next
    INDEX
    Explanations

    references to statistics, specifically those related to performance metrics over the years

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

    a specific year

    np_acts-logits-general · gemini-2.0-flash

    last year or season

    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
    urlpatterns
    -0.60
    elemField
    -0.51
    SequentialGroup
    -0.51
    WebElementEntity
    -0.49
    Autoritní
    -0.48
    XmlAccessorType
    -0.48
    !*\
    -0.48
    tableCell
    -0.47
    uxxxx
    -0.47
    GTCX
    -0.46
    POSITIVE LOGITS
     year
    0.78
     Year
    0.77
    Year
    0.70
     mwaka
    0.65
     anuales
    0.65
     season
    0.64
     året
    0.64
     YEAR
    0.62
     année
    0.61
     vuoden
    0.61
    Activations Density 0.394%

    No Known Activations