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. 3-GEMMASCOPE-RES-16K
    6. 10866
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Daniel" and references to electricity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jLabel
    -0.89
    Hauptartikel
    -0.86
     CommonModule
    -0.85
     kasarigan
    -0.81
     resourceCulture
    -0.81
    BorderFactory
    -0.80
     Ibero
    -0.80
     Milford
    -0.79
    Folks
    -0.79
     Monfieur
    -0.76
    POSITIVE LOGITS
     jacket
    0.93
               
    0.84
    Daniel
    0.84
     Jacket
    0.84
     Daniel
    0.83
     electricity
    0.80
     Electricity
    0.76
     jackets
    0.73
     Ruiz
    0.73
     Cuc
    0.71
    Activations Density 0.133%

    No Known Activations