© 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. 14926
    Prev
    Next
    INDEX
    Explanations

    interrogative words and phrases that signal questions or inquiries

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

    Asks "how," "why," or "where"

    np_acts-logits-general · gemini-2.0-flash

    when, where, how, why

    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
    UnusedPrivate
    -0.87
    msgTypes
    -0.78
     كومونز
    -0.75
    twimg
    -0.62
     jsPsych
    -0.61
    tagHelperRunner
    -0.60
    ."</
    -0.59
    WireFormatLite
    -0.59
    rawDesc
    -0.58
    SharedCtor
    -0.57
    POSITIVE LOGITS
    why
    1.19
     why
    1.16
    where
    1.13
    how
    1.11
     how
    1.06
     HOW
    1.05
    Where
    1.04
     WHY
    1.02
    WHY
    1.02
     WHERE
    0.99
    Activations Density 0.149%

    No Known Activations