© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2761
    Prev
    Next
    INDEX
    Explanations

    references to environmental conditions, specifically related to tropics and weather patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HFILL
    -0.46
     AssemblyTitle
    -0.45
     архивлан
    -0.45
     overras
    -0.38
    Viited
    -0.37
     Schra
    -0.36
     članak
    -0.35
     Exacts
    -0.35
    DMETHOD
    -0.35
     Wachs
    -0.35
    POSITIVE LOGITS
    Trop
    0.73
    trop
    0.69
     tropical
    0.69
    tropical
    0.68
    Peel
    0.67
     peel
    0.66
     Tropical
    0.65
     tropics
    0.65
     melt
    0.64
     Trop
    0.64
    Activations Density 0.493%

    No Known Activations