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. 719
    Prev
    Next
    INDEX
    Explanations

    references to authority figures and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Skocz
    -0.50
     متعلقه
    -0.46
     Hunt
    -0.46
     contract
    -0.44
     mesure
    -0.43
    TagMode
    -0.43
     Valhalla
    -0.41
     Alger
    -0.41
    ipal
    -0.41
    Contract
    -0.40
    POSITIVE LOGITS
     Galilee
    0.78
     disciples
    0.78
     Disciples
    0.74
    WebServlet
    0.72
     Galile
    0.72
     Jesus
    0.68
     propOrder
    0.67
     Magdalene
    0.67
     Judea
    0.66
     بيها
    0.66
    Activations Density 0.109%

    No Known Activations