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. 6482
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or inquiries

    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
     Мексичка
    -0.71
    Попис
    -0.65
     propOrder
    -0.63
    ientôt
    -0.54
    AsUp
    -0.54
     gddr
    -0.52
    orologio
    -0.51
    bodyParser
    -0.51
    enapa
    -0.51
    Rohy
    -0.50
    POSITIVE LOGITS
     contact
    2.02
     Contact
    1.78
    contact
    1.71
    Contact
    1.68
     CONTACT
    1.57
    CONTACT
    1.42
     contacts
    1.27
     kontakt
    1.25
     contacting
    1.22
     kontak
    1.19
    Activations Density 0.126%

    No Known Activations