© 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. 14-GEMMASCOPE-RES-16K
    11. 3204
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of new thoughts or sections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.93
    省市镇
    -0.58
     kasarigan
    -0.57
    writeFieldEnd
    -0.57
     unknownFields
    -0.56
     moteurs
    -0.52
    millimeters
    -0.51
     demand
    -0.51
    setVerticalGroup
    -0.51
    mentet
    -0.49
    POSITIVE LOGITS
    onViewCreated
    0.90
    出版年
    0.88
    UserScript
    0.84
    AccessFile
    0.68
    HtmlAttribute
    0.65
    تقاوى
    0.64
    findpost
    0.62
     ostavi
    0.61
    Hochspringen
    0.61
    Архівовано
    0.61
    Activations Density 0.103%

    No Known Activations