© 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. 20-GEMMASCOPE-RES-16K
    11. 16096
    Prev
    Next
    INDEX
    Explanations

    Roman numeral headings and legal document sections

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

    Roman numeral IV or III

    np_acts-logits-general · gemini-2.0-flash

    Roman numeral section dividers

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Top
    -0.58
    UnusedPrivate
    -0.56
    Top
    -0.54
     bluse
    -0.49
     TOP
    -0.49
    তথ্যসূত্র
    -0.48
    tops
    -0.47
     top
    -0.46
    ServiceModel
    -0.46
    TOP
    -0.45
    POSITIVE LOGITS
     ligiloj
    0.65
     للمعارف
    0.62
     unknownFields
    0.60
     كومونز
    0.57
    存于互联网档案馆
    0.55
    revalidate
    0.55
     transfieras
    0.53
     ddelweddau
    0.52
     Winaray
    0.52
     pouches
    0.51
    Activations Density 0.073%

    No Known Activations