© 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. 10690
    Prev
    Next
    INDEX
    Explanations

    references to non-public APIs and their usage constraints

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

    followed by "by" or "behaviour"

    np_acts-logits-general · gemini-2.0-flash

    overriding or defining behavior

    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
    这是一
    -0.44
    HtmlAttribute
    -0.44
     GOTO
    -0.43
     sequelize
    -0.43
    fromJson
    -0.42
     ch
    -0.41
    ző
    -0.40
    MinWidth
    -0.40
    StatusOK
    -0.39
     tadi
    -0.39
    POSITIVE LOGITS
     implementation
    1.02
     compatibility
    0.95
     implementations
    0.95
    implementation
    0.90
    compatibility
    0.89
     implement
    0.87
    behaviour
    0.85
    implement
    0.84
     indisponible
    0.84
     behaviour
    0.83
    Activations Density 0.926%

    No Known Activations