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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15458
    Prev
    Next
    INDEX
    Explanations

    the Japanese word for "you" or related expressions of address

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

    Japanese "o"

    np_acts-logits-general · gemini-2.0-flash

    japanese honorifics or code formatting

    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
    lapsingToolbar
    -0.68
    :+:
    -0.61
    ByVersion
    -0.58
    QMetaType
    -0.58
    formaz
    -0.58
     ficha
    -0.58
    詫
    -0.58
     Varieties
    -0.57
     ویکی‌پدیا
    -0.56
     saveur
    -0.56
    POSITIVE LOGITS
     Yule
    0.48
     Transvaal
    0.48
     pleaſure
    0.47
    endphp
    0.47
    OpenHelper
    0.47
     infantile
    0.46
    agascar
    0.46
     Caspian
    0.46
    oxone
    0.45
     FSB
    0.45
    Activations Density 0.035%

    No Known Activations