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. 1711
    Prev
    Next
    INDEX
    Explanations

    names of organizations and entities related to healthcare and community services

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

    Preceding company or brand names

    np_acts-logits-general · gemini-2.0-flash

    company partnerships,journalists, or historical sites

    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
    PreferredItem
    -0.81
    apparently
    -0.64
    protoimpl
    -0.63
    AddTagHelper
    -0.60
     Apparently
    -0.57
    Apparently
    -0.56
    SharedCtor
    -0.52
     Roskov
    -0.52
    oplayer
    -0.52
     kaarangay
    -0.52
    POSITIVE LOGITS
     staff
    0.85
     Staff
    0.73
     strives
    0.73
     proudly
    0.72
    これからも
    0.70
     welcomes
    0.69
    ®
    0.65
     prides
    0.64
     staffs
    0.63
    Staff
    0.63
    Activations Density 0.230%

    No Known Activations