© 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. 4-GEMMASCOPE-RES-16K
    11. 10708
    Prev
    Next
    INDEX
    Explanations

    statements of authorship and declarations of no conflict of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.99
    CodedInputStream
    -0.97
    ValueStyle
    -0.97
    Билгалдахарш
    -0.96
    MigrationBuilder
    -0.94
     архивлан
    -0.92
    UnusedPrivate
    -0.89
    writeField
    -0.89
     AssemblyCulture
    -0.86
    Portail
    -0.85
    POSITIVE LOGITS
     '
    0.49
     ä
    0.46
    arxiv
    0.46
    ['
    0.43
     Dis
    0.42
     ‘
    0.41
     lat
    0.40
    ]['
    0.40
     Ng
    0.40
    arn
    0.40
    Activations Density 0.052%

    No Known Activations