© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 474
    Prev
    Next
    INDEX
    Explanations

    markers related to program initiation and product notifications

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

    the beginning of a new section or paragraph in the text

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

    product reveals, updates, variations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     slutt
    -0.47
    יין
    -0.45
    withId
    -0.42
    uruhan
    -0.40
     Those
    -0.40
    ΕΙ
    -0.40
    anyone
    -0.39
     respec
    -0.39
     catatan
    -0.39
    件
    -0.39
    POSITIVE LOGITS
    脚注の使い方
    0.93
    Personendaten
    0.77
     updates
    0.75
     kaarangay
    0.72
    findpost
    0.72
    TagMode
    0.70
    出版年
    0.70
     للمعارف
    0.69
     كومونز
    0.69
     propOrder
    0.68
    Activations Density 0.045%

    No Known Activations