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. 21-GEMMASCOPE-RES-16K
    6. 6587
    Prev
    Next
    INDEX
    Explanations

    terms and references related to court and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nawr
    -0.66
    AddTagHelper
    -0.64
    TagMode
    -0.56
     تضيفلها
    -0.56
    Carriera
    -0.55
    Gerd
    -0.52
    principalTable
    -0.51
     Vater
    -0.51
    suff
    -0.51
    ontale
    -0.51
    POSITIVE LOGITS
    rooms
    0.80
    room
    0.74
     docket
    0.72
    ESY
    0.68
    ROOM
    0.65
     JSTOR
    0.60
    martial
    0.58
    الإنجليزية
    0.58
    barkeit
    0.57
     smtplib
    0.57
    Activations Density 0.174%

    No Known Activations