© 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. 23-GEMMASCOPE-RES-16K
    11. 6785
    Prev
    Next
    INDEX
    Explanations

    numerical values related to performance metrics and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lèvres
    -0.84
     dépens
    -0.77
     fermés
    -0.75
     prêtres
    -0.75
     pères
    -0.74
     незавершена
    -0.70
     enfans
    -0.69
     âmes
    -0.69
     vœux
    -0.69
     traités
    -0.69
    POSITIVE LOGITS
    %
    0.79
    +%
    0.73
     instead
    0.69
     times
    0.68
     examples
    0.65
    x
    0.65
     units
    0.63
    %+
    0.63
     fewer
    0.63
    %-
    0.62
    Activations Density 1.201%

    No Known Activations