© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6761
    Prev
    Next
    INDEX
    Explanations

    words related to sizes and measurements in various contexts

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

    following "small" or "smaller"

    np_acts-logits-general · gemini-2.0-flash

    smallness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.71
     Signalez
    -0.60
    contentLoaded
    -0.59
     дописавши
    -0.56
     ویکی‌پدیا
    -0.55
     Roskov
    -0.55
     ModelExpression
    -0.54
     transférez
    -0.53
    mybatisplus
    -0.52
    ậc
    -0.51
    POSITIVE LOGITS
     small
    3.20
    small
    2.91
     smaller
    2.89
    Small
    2.87
     tiny
    2.87
     Small
    2.75
     SMALL
    2.75
    Smaller
    2.60
     Smaller
    2.59
    SMALL
    2.59
    Activations Density 0.965%

    No Known Activations