© 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. 10416
    Prev
    Next
    INDEX
    Explanations

    numerical values related to time, height, weight, and other measurements

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

    Numbers followed by units of time or distance

    np_acts-logits-general · gemini-2.0-flash

    feet and inches

    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
     kasarigan
    -0.82
     مشين
    -0.72
     Wikimedijinoj
    -0.72
     صوتيه
    -0.72
    ArrowToggle
    -0.69
    MENAFN
    -0.68
    TintMode
    -0.67
     للمعارف
    -0.66
    LookAnd
    -0.65
    Chham
    -0.65
    POSITIVE LOGITS
     
    0.66
    เศษ
    0.55
    零
    0.53
    اریخ
    0.53
     outstanding
    0.45
     per
    0.45
     零
    0.44
    nove
    0.44
     sharp
    0.43
    complexContent
    0.43
    Activations Density 0.227%

    No Known Activations