© 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. 9080
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty or affirmation

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

    Adverbs indicating certainty

    np_acts-logits-general · gemini-2.0-flash

    certainly, definitely, clearly

    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
     actually
    -1.10
    actually
    -1.04
     Actually
    -0.95
    Actually
    -0.95
     apparently
    -0.94
     basically
    -0.88
     ACTUALLY
    -0.86
    Basically
    -0.85
     Basically
    -0.85
    意外と
    -0.83
    POSITIVE LOGITS
    Архівовано
    0.69
    EditorBrowsable
    0.67
     MessageBoxIcon
    0.66
    ConstraintMaker
    0.62
    unkt
    0.61
    saraba
    0.61
    writeFieldEnd
    0.60
    aarrggbb
    0.60
    しも
    0.59
     فريبيس
    0.59
    Activations Density 0.226%

    No Known Activations