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. 11-GEMMASCOPE-RES-16K
    6. 7443
    Prev
    Next
    INDEX
    Explanations

    context-related keywords in programming configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -1.00
     EconPapers
    -0.95
    GEBURTSDATUM
    -0.87
     createState
    -0.83
    ymce
    -0.83
    InvalidProtocol
    -0.80
    EndInit
    -0.80
    BeginInit
    -0.78
     sledge
    -0.77
    TagHelpers
    -0.77
    POSITIVE LOGITS
     Duckworth
    0.80
     Williams
    0.79
    Williams
    0.78
     Williamsburg
    0.77
     Weinberg
    0.77
     ctx
    0.75
     groves
    0.70
    ctx
    0.67
    Tags
    0.66
     peel
    0.66
    Activations Density 0.709%

    No Known Activations