© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5541
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical modeling and estimation techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.54
    MigrationBuilder
    -0.52
    DllImport
    -0.47
     الحره
    -0.47
    baller
    -0.46
     DialogInterface
    -0.46
    raiser
    -0.46
     миллионов
    -0.46
    EqualsAnd
    -0.46
     aload
    -0.45
    POSITIVE LOGITS
     trend
    0.89
    Trend
    0.85
    trend
    0.84
     Trend
    0.80
     season
    0.78
     Granger
    0.74
     series
    0.71
     seasonal
    0.71
     Seasonal
    0.68
    Season
    0.68
    Activations Density 1.313%

    No Known Activations