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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8985
    Prev
    Next
    INDEX
    Explanations

    references to wind and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to "wind" in various contexts, particularly weather phenomena, turbines, and aerodynamic testing.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "wind" appearing in various contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colgar
    -0.37
     rozgry
    -0.35
     consciência
    -0.34
     dziecka
    -0.34
     atraer
    -0.33
     parfaite
    -0.32
     asegurar
    -0.32
     leçon
    -0.32
     leçons
    -0.32
     sahip
    -0.31
    POSITIVE LOGITS
     Wind
    1.06
    Wind
    1.00
     WIND
    0.97
    WIND
    0.96
     wind
    0.88
    wind
    0.85
     windmill
    0.77
     Windy
    0.75
    blown
    0.74
     Vind
    0.73
    Activations Density 0.063%

    No Known Activations