© 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. 20-GEMMASCOPE-RES-16K
    11. 5425
    Prev
    Next
    INDEX
    Explanations

    structured programming statements and variable declarations

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

    Code-related keywords and syntax

    np_acts-logits-general · gemini-2.0-flash

    programming code and licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toolStrip
    -0.51
    ạn
    -0.47
    cherichia
    -0.47
    indexPath
    -0.47
     ander
    -0.47
     getArguments
    -0.46
     therefore
    -0.46
    essen
    -0.45
     spectator
    -0.44
    fören
    -0.43
    POSITIVE LOGITS
    bool
    0.73
     bool
    0.72
    late
    0.69
     ویکی‌پدیای
    0.66
     String
    0.65
    .*")]
    0.63
    󠁿
    0.61
     final
    0.61
     kasarigan
    0.61
     }}"></
    0.60
    Activations Density 0.036%

    No Known Activations