© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 8545
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section transitions, indicating changes in content or focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.73
    esgue
    -0.67
     foon
    -0.65
     sherds
    -0.65
    ppure
    -0.64
    malıdır
    -0.64
     Doch
    -0.63
    MMV
    -0.62
     tvb
    -0.62
     ―――――
    -0.62
    POSITIVE LOGITS
     basically
    0.87
     that
    0.80
     really
    0.79
     very
    0.78
     [
    0.74
     because
    0.74
     I
    0.71
     everybody
    0.70
    Everybody
    0.69
    basically
    0.69
    Activations Density 0.079%

    No Known Activations