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. 2373
    Prev
    Next
    INDEX
    Explanations

    links and references to online resources, particularly related to programming and code repositories

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

    Commands or file paths

    np_acts-logits-general · gemini-2.0-flash

    docker, kubernetes, npm, runner

    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
    struts
    -0.66
    Xna
    -0.55
     Archivado
    -0.55
     cannibal
    -0.54
    ejb
    -0.54
     onPostExecute
    -0.52
     Gump
    -0.50
     artistico
    -0.50
     intitulé
    -0.50
     ActiveX
    -0.50
    POSITIVE LOGITS
     autorytatywna
    0.78
    tvguidetime
    0.71
     disambiguazione
    0.70
     Rust
    0.66
    MigrationBuilder
    0.65
     otomatig
    0.63
    dflare
    0.63
     ecosystem
    0.63
     transfieras
    0.62
     repro
    0.62
    Activations Density 1.810%

    No Known Activations