© 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. 30-GEMMASCOPE-RES-16K
    11. 10910
    Prev
    Next
    INDEX
    Explanations

    descriptions of environmental conditions, particularly related to wind

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

    wind direction and speed

    np_acts-logits-general · gemini-2.0-flash

    wind and its speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.66
    AndEndTag
    -0.60
     Picchu
    -0.45
    ignoire
    -0.44
     defaultstate
    -0.44
    rąg
    -0.43
    ингл
    -0.41
    Демографія
    -0.41
     Witkin
    -0.40
     Rowley
    -0.40
    POSITIVE LOGITS
     wind
    2.16
     winds
    1.85
     Wind
    1.84
    Wind
    1.78
    wind
    1.77
     WIND
    1.63
     Winds
    1.60
    WIND
    1.50
    Winds
    1.48
    winds
    1.43
    Activations Density 0.192%

    No Known Activations