© 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. 4034
    Prev
    Next
    INDEX
    Explanations

    instances of the word "par", particularly in varying contexts and combinations

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

    starting with "par"

    np_acts-logits-general · gemini-2.0-flash

    parody, paradisaical, Paraguayan, parakeet, paradoxical, parole, particulate, paralogous

    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
     Roskov
    -0.76
     الرياضيه
    -0.72
    UnknownFields
    -0.71
    modb
    -0.68
    labus
    -0.67
     Wikimedijinoj
    -0.67
    twimg
    -0.66
    googleapis
    -0.63
    queryInterface
    -0.63
     ویکی‌آمباردا
    -0.62
    POSITIVE LOGITS
     par
    0.83
     Par
    0.81
    par
    0.79
    Par
    0.73
     PAR
    0.69
    PAR
    0.63
     CGRectMake
    0.56
     Pars
    0.54
     Pari
    0.53
     parlor
    0.51
    Activations Density 0.050%

    No Known Activations