© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16353
    Prev
    Next
    INDEX
    Explanations

    contexts involving significant legal or bureaucratic actions

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

    HTML heading tags (h1-h6), bolding, or underlines

    np_acts-logits-general · gemini-2.0-flash

    sentence boundary detection

    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
     متعلقه
    -0.79
    Ibid
    -0.67
    abestanden
    -0.65
     useHistory
    -0.65
     Ibid
    -0.65
    HasForeignKey
    -0.64
     الحره
    -0.64
    出版年
    -0.62
    archiviato
    -0.60
    EndInit
    -0.59
    POSITIVE LOGITS
    <strong>
    0.93
    <b>
    0.89
    <h3>
    0.81
    <u>
    0.78
    <h5>
    0.75
    <h2>
    0.69
    ↵↵
    0.66
    matische
    0.64
     argint
    0.61
    <h6>
    0.60
    Activations Density 0.441%

    No Known Activations