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. 2102
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly in a scientific or quantitative context

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

    The number "6" (sometimes superscript)

    np_acts-logits-general · gemini-2.0-flash

    numbers and "Sixers"

    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
    ibatis
    -0.86
    andExpect
    -0.85
     Legg
    -0.81
    yarnpkg
    -0.79
    ukone
    -0.75
    errHandler
    -0.75
     مُعرِّف
    -0.75
    ので
    -0.72
     ویکی‌آمباردا
    -0.71
    ceous
    -0.71
    POSITIVE LOGITS
    6
    1.17
    ers
    0.84
    ⁶
    0.78
    7
    0.75
     Sixers
    0.73
    5
    0.72
    8
    0.68
    4
    0.68
    SIX
    0.66
    ERS
    0.66
    Activations Density 0.871%

    No Known Activations