© 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. 31-GEMMASCOPE-RES-16K
    11. 7427
    Prev
    Next
    INDEX
    Explanations

    references to time-sensitive events, especially related to gatherings or occasions

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

    temporal references to specific times of day, particularly evening and night hours.

    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
     Lunch
    -0.96
    Lunch
    -0.94
     lunch
    -0.94
    lunch
    -0.80
     noon
    -0.77
     sunny
    -0.75
     LUNCH
    -0.74
     lunches
    -0.73
    午餐
    -0.72
     midday
    -0.70
    POSITIVE LOGITS
     night
    2.20
    Night
    1.95
    night
    1.95
     Night
    1.94
     nights
    1.92
     tonight
    1.89
     NIGHT
    1.86
     nightly
    1.84
    Tonight
    1.76
     nighttime
    1.76
    Activations Density 0.531%

    No Known Activations