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. 2403
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements, particularly those related to doses and quantities

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

    Numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units or time

    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
     كومونز
    -0.87
    twimg
    -0.61
     disambiguazione
    -0.56
    igshid
    -0.56
    )++;
    -0.54
     kasarigan
    -0.53
     ͡°)
    -0.51
    Datuak
    -0.51
    PreferredItem
    -0.51
    исленность
    -0.50
    POSITIVE LOGITS
    province
    0.58
     grids
    0.57
     literate
    0.56
     tempio
    0.56
    ühen
    0.54
    vician
    0.54
    ixeira
    0.54
    NewUrlParser
    0.53
     Darius
    0.52
    zension
    0.52
    Activations Density 0.194%

    No Known Activations