© 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. 11-GEMMASCOPE-RES-16K
    11. 13049
    Prev
    Next
    INDEX
    Explanations

    specific scientific data and terminology related to research and medical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.15
    ThroughAttribute
    -1.02
    tagHelperRunner
    -0.97
    +:+
    -0.95
    SourceChecksum
    -0.95
     MainAxisSize
    -0.93
    WebElementEntity
    -0.92
     '\\;'
    -0.91
     "..\..\..\
    -0.89
    expandindo
    -0.88
    POSITIVE LOGITS
     diatas
    0.48
    stat
    0.41
     Graf
    0.40
    Ow
    0.40
    所示
    0.39
    ow
    0.38
     Parsons
    0.38
     items
    0.38
     except
    0.37
     balas
    0.37
    Activations Density 0.704%

    No Known Activations