Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12666
    Prev
    Next
    INDEX
    Explanations

    references to specific U.S. states

    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
     ostavi
    -0.65
     Roskov
    -0.61
    AddHtmlAttribute
    -0.60
     Gerente
    -0.60
    principalTable
    -0.57
    [++
    -0.55
    ազմ
    -0.55
     redund
    -0.54
    tfrac
    -0.54
     hereof
    -0.53
    POSITIVE LOGITS
     Texas
    1.88
     Georgia
    1.80
     Illinois
    1.78
     Pennsylvania
    1.76
     Tennessee
    1.74
     Florida
    1.73
     Louisiana
    1.71
     Wisconsin
    1.70
     Maryland
    1.68
     Virginia
    1.67
    Activations Density 0.108%

    No Known Activations