© 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. 2537
    Prev
    Next
    INDEX
    Explanations

    non-zero activation values that indicate significant content or entry points in the text

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

    Code, programming, and scripting related tokens

    np_acts-logits-general · gemini-2.0-flash

    code keywords and separators

    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
    ++
    -0.59
     ()
    -0.46
    _
    -0.44
    irchen
    -0.44
    %
    -0.41
    ".
    -0.41
    []
    -0.40
    AKER
    -0.39
    $.
    -0.39
     Commencez
    -0.39
    POSITIVE LOGITS
    class
    0.69
    import
    0.68
    def
    0.67
        
    0.65
     import
    0.65
    function
    0.64
     class
    0.61
    MigrationBuilder
    0.60
    public
    0.60
     def
    0.60
    Activations Density 0.438%

    No Known Activations