© 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. 6262
    Prev
    Next
    INDEX
    Explanations

    greetings and informal salutations

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

    Follows "Hi" or "hi" and a punctuation mark or name

    np_acts-logits-general · gemini-2.0-flash

    greetings and names

    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
     שוליים
    -0.59
    лива
    -0.52
    localObject
    -0.52
    <h6>
    -0.52
    UserScript
    -0.50
    antz
    -0.49
    sed
    -0.49
    :+:
    -0.48
    bindParam
    -0.48
    וז
    -0.48
    POSITIVE LOGITS
     Hiber
    0.70
     Hiram
    0.70
     виправивши
    0.69
     pleaſure
    0.68
     Abhi
    0.63
     Hipp
    0.61
    </tfoot>
    0.61
     thither
    0.60
     myſelf
    0.60
    PYX
    0.59
    Activations Density 0.083%

    No Known Activations