© 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. 536
    Prev
    Next
    INDEX
    Explanations

    terms related to wild animals, particularly wild horses

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

    "Wild" followed by animals or types

    np_acts-logits-general · gemini-2.0-flash

    wild type, wild horse, wild west

    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
     незавершена
    -0.80
    cshtml
    -0.72
    cotch
    -0.69
    \{\\
    -0.68
     consultato
    -0.66
    RTEX
    -0.66
    djangoproject
    -0.65
     GetEnumerator
    -0.64
     كومونز
    -0.63
    veless
    -0.62
    POSITIVE LOGITS
     wild
    1.02
    Wild
    0.94
     WILD
    0.92
     Wild
    0.92
    WILD
    0.90
    wild
    0.88
    cat
    0.71
     boar
    0.64
     wilder
    0.63
     salvaje
    0.63
    Activations Density 0.077%

    No Known Activations