Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13727
    Prev
    Next
    INDEX
    Explanations

    elements and structures in programming code such as function declarations and variable assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.82
     <>",
    -0.72
    TestingModule
    -0.72
    Tembelea
    -0.68
     للمعارف
    -0.67
    Datuak
    -0.66
    webElementXpaths
    -0.66
    ⓘ
    -0.66
     становника
    -0.65
     ")");
    -0.65
    POSITIVE LOGITS
    [
    1.04
    [-
    0.83
     first
    0.78
     [
    0.78
    '][
    0.77
    ()[
    0.77
     $[
    0.67
    ')[
    0.67
    first
    0.66
    "][
    0.65
    Activations Density 0.142%

    No Known Activations