Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1764
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions or organizations in the context of academic or clinical research

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

    ending in "a" or "arri"

    np_acts-logits-general · gemini-2.0-flash

    Basque and Spanish 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
     виправивши
    -0.59
     aérienne
    -0.54
     AssemblyCulture
    -0.53
     فريبيس
    -0.53
    älv
    -0.49
     étendue
    -0.49
     Antalya
    -0.47
    drawSprites
    -0.47
     ویکی‌پدیای
    -0.47
     Mejía
    -0.47
    POSITIVE LOGITS
    tx
    0.76
     tx
    0.75
     Tx
    0.74
    Tx
    0.68
     eta
    0.64
    ⓧ
    0.59
     bat
    0.56
     Zub
    0.55
    MoveNext
    0.55
    eus
    0.55
    Activations Density 0.041%

    No Known Activations