© 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. 7110
    Prev
    Next
    INDEX
    Explanations

    terms related to export and trade controls

    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
    sz
    -0.63
    TestMethod
    -0.58
     nắm
    -0.58
    DatabaseError
    -0.56
     man
    -0.56
    tvguidetime
    -0.56
    LayoutConstraint
    -0.56
    Câu
    -0.55
     plais
    -0.54
    AMIENTO
    -0.54
    POSITIVE LOGITS
     Exports
    1.48
     exports
    1.45
    Exports
    1.41
    exports
    1.37
     Export
    1.24
    Export
    1.24
     EXPORT
    1.22
     export
    1.17
     exportation
    1.16
    EXPORT
    1.14
    Activations Density 0.041%

    No Known Activations