© 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. 22-GEMMASCOPE-RES-16K
    11. 5090
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or possibility

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

    Comes before hedges/qualifiers

    np_acts-logits-general · gemini-2.0-flash

    perhaps, maybe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    probably
    -0.70
     probably
    -0.69
     apparently
    -0.67
    presumably
    -0.66
     presumably
    -0.65
     probabilmente
    -0.65
     Probably
    -0.64
    apparently
    -0.61
     probablemente
    -0.61
     Presumably
    -0.60
    POSITIVE LOGITS
     even
    0.88
     someday
    0.75
     not
    0.73
     sogar
    0.72
    even
    0.72
     unsur
    0.69
     saja
    0.67
    hould
    0.65
     jopa
    0.65
    anskje
    0.64
    Activations Density 0.108%

    No Known Activations