© 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. 18-GEMMASCOPE-RES-16K
    11. 6634
    Prev
    Next
    INDEX
    Explanations

    terms related to trade regulations and exports

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

    Code-related terms: imports, exports

    np_acts-logits-general · gemini-2.0-flash

    exports and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.69
    "]);
    -0.67
    tagHelper
    -0.64
     snippetHide
    -0.63
    tagHelperRunner
    -0.59
     HttpNotFound
    -0.59
    )");
    -0.58
    المكان
    -0.57
    setVerticalGroup
    -0.56
    ")));
    -0.55
    POSITIVE LOGITS
     export
    2.14
     exports
    2.00
     import
    1.92
     Export
    1.92
     exporting
    1.90
     exported
    1.88
     imports
    1.77
     Exports
    1.76
    export
    1.76
     importing
    1.73
    Activations Density 0.226%

    No Known Activations