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

    Neuronpedia

    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. 11598
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific name or entity, likely a person or character, consistently recognized throughout the text

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

    starting with "Hy" or "hy"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Hy

    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
    日閲覧
    -0.98
    InjectAttribute
    -0.83
     AssemblyCulture
    -0.80
    #
    -0.78
    endphp
    -0.77
     Normdatei
    -0.76
     ErrIntOverflow
    -0.76
    AutoScaleMode
    -0.75
    ⓧ
    -0.72
    sizeCache
    -0.72
    POSITIVE LOGITS
     Hy
    1.14
    Hy
    1.05
     hy
    1.04
    hy
    0.93
     HY
    0.89
    HY
    0.64
     Hyatt
    0.55
     Hyster
    0.54
    phal
    0.49
    arul
    0.49
    Activations Density 0.071%

    No Known Activations