© 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. 24-GEMMASCOPE-RES-16K
    11. 13791
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and constructs related to function definitions and access modifiers

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

    Variable declarations and type annotations

    np_acts-logits-general · gemini-2.0-flash

    programming code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.65
    AutoScaleMode
    -0.52
    ]^{-
    -0.50
     ust
    -0.47
    wpi
    -0.47
     ${
    -0.46
    MigrationBuilder
    -0.45
    asion
    -0.44
    گذ
    -0.44
    ]^{\
    -0.44
    POSITIVE LOGITS
    final
    1.05
    late
    0.98
    bool
    0.91
     final
    0.90
    Future
    0.90
    void
    0.86
     Future
    0.77
     late
    0.77
     bool
    0.77
    String
    0.74
    Activations Density 0.040%

    No Known Activations