© 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. 18-GEMMASCOPE-RES-16K
    11. 1831
    Prev
    Next
    INDEX
    Explanations

    numerical data presented in context, especially related to percentages and ratios

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

    Percentages and numbers with parentheses

    np_acts-logits-general · gemini-2.0-flash

    percentages and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phazard
    -0.55
    #![
    -0.47
    ynh
    -0.47
    gher
    -0.47
    caz
    -0.46
     wat
    -0.46
     much
    -0.46
    Мекси
    -0.45
    mung
    -0.44
     into
    -0.44
    POSITIVE LOGITS
     BoxFit
    0.92
    ValueStyle
    0.86
     Efq
    0.84
     ſeveral
    0.78
    )».
    0.78
     câte
    0.77
     ujednoznacz
    0.76
    MigrationBuilder
    0.75
    存于互联网档案馆
    0.75
     ویکی‌پدیای
    0.69
    Activations Density 0.195%

    No Known Activations