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. 9-GEMMASCOPE-RES-16K
    6. 15441
    Prev
    Next
    INDEX
    Explanations

    instances of quotes and their surrounding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /\.(
    -0.81
    AlterField
    -0.79
    IContainer
    -0.73
    Tembelea
    -0.71
    ness
    -0.69
     CEM
    -0.68
     [{
    
    -0.67
    modelBuilder
    -0.67
     Terraria
    -0.66
     Auger
    -0.66
    POSITIVE LOGITS
     quote
    1.83
     quotes
    1.80
     Quote
    1.68
    quote
    1.68
    Quote
    1.60
    Quotes
    1.56
     QUOTE
    1.55
    quotes
    1.54
     quoted
    1.53
     quoting
    1.51
    Activations Density 0.097%

    No Known Activations