© 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. 6850
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "number."

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

    "number of"

    np_acts-logits-general · gemini-2.0-flash

    number of

    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
    UnsafeEnabled
    -0.77
     <>",
    -0.73
    клопе
    -0.71
     intptr
    -0.69
    Примітки
    -0.68
     /\.(
    -0.67
     BrowserModule
    -0.63
    )++;
    -0.63
    openConnection
    -0.62
    مقاله
    -0.62
    POSITIVE LOGITS
     of
    0.72
    __*/
    0.52
    arraycopy
    0.47
    ביוגרפיה
    0.44
    ʊ
    0.43
    DispatchToProps
    0.41
    inflater
    0.41
     gồm
    0.41
     including
    0.41
    рых
    0.39
    Activations Density 0.196%

    No Known Activations