© 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. 5918
    Prev
    Next
    INDEX
    Explanations

    HTML header tags indicating section titles or important headings

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

    HTML heading tags (h3, h4)

    np_acts-logits-general · gemini-2.0-flash

    programming documentation headings

    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
    ers
    -0.88
    WindowConstants
    -0.82
     esternos
    -0.74
    ","","
    -0.67
    PROMOTED
    -0.66
    />";
    -0.65
     Torre
    -0.64
    <h2>
    -0.64
    {}",
    -0.63
    дів
    -0.63
    POSITIVE LOGITS
     Jefus
    1.06
     dieux
    0.99
     itſelf
    0.91
     myſelf
    0.91
    <h3>
    0.89
     Shakspeare
    0.88
    Viitteet
    0.87
     Cæsar
    0.83
     Chriſt
    0.83
     EIS
    0.81
    Activations Density 0.049%

    No Known Activations