© 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. 37-GEMMASCOPE-RES-16K
    11. 4717
    Prev
    Next
    INDEX
    Explanations

    expressions related to seasonal changes and celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     October
    -0.84
    🎃
    -0.83
     September
    -0.83
     OCTOBER
    -0.81
    October
    -0.79
     CHRISTMAS
    -0.78
     November
    -0.78
     Halloween
    -0.78
     August
    -0.77
    OCTOBER
    -0.77
    POSITIVE LOGITS
     spring
    2.20
     Spring
    2.02
    Spring
    2.00
    spring
    1.87
     SPRING
    1.80
     springtime
    1.77
    April
    1.75
     April
    1.73
    SPRING
    1.69
    APRIL
    1.49
    Activations Density 0.475%

    No Known Activations