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. 12083
    Prev
    Next
    INDEX
    Explanations

    references to companies and organizations, especially in a business context

    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
     Picchu
    -0.81
    yntaxException
    -0.73
    setVerticalGroup
    -0.69
    richTextPanel
    -0.67
    ced
    -0.67
    enumi
    -0.66
    abetes
    -0.66
    ]")]
    -0.66
     InputDecoration
    -0.65
    ———
    -0.64
    POSITIVE LOGITS
    wide
    0.75
    aderie
    0.71
     pany
    0.67
    Companies
    0.66
    berdayakan
    0.66
     companies
    0.66
     Companies
    0.65
    的公司
    0.63
    perusahaan
    0.60
    companies
    0.59
    Activations Density 0.145%

    No Known Activations