Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10108
    Prev
    Next
    INDEX
    Explanations

    questions and references to uncertainty or confusion

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

    Japanese text followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    japanese, chinese, and english phrases

    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
    ,
    -0.82
     a
    -0.80
     here
    -0.73
     and
    -0.73
     est
    -0.72
     in
    -0.72
     as
    -0.69
     on
    -0.67
     de
    -0.67
     is
    -0.67
    POSITIVE LOGITS
     ainfi
    0.98
     auffi
    0.97
     itſelf
    0.93
     plufieurs
    0.93
    GraphicsUnit
    0.91
     myſelf
    0.91
     Anſ
    0.89
     ―――――
    0.89
     PTS
    0.89
     crdi
    0.88
    Activations Density 0.004%

    No Known Activations