© 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. 11994
    Prev
    Next
    INDEX
    Explanations

    output statements in code, specifically those that print or display variable values and messages

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

    Code, namespaces, or special characters

    np_acts-logits-general · gemini-2.0-flash

    output operator <<

    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
     mil
    -0.55
    JKLM
    -0.52
     ${
    -0.49
    χα
    -0.48
    mil
    -0.48
    ${
    -0.47
    ganos
    -0.47
    作
    -0.47
    MIL
    -0.46
    kah
    -0.46
    POSITIVE LOGITS
     <<
    1.19
    Personensuche
    0.97
    ]<<
    0.94
    )<<
    0.94
    <<
    0.93
    ()<<
    0.87
    <<(
    0.78
    ఔ
    0.72
    AccessorTable
    0.67
    帖最后由
    0.63
    Activations Density 0.071%

    No Known Activations