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

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 5936
    Prev
    Next
    INDEX
    Explanations

    specific time-related phrases and contexts, particularly those involving lunchtime and media scheduling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nightly
    -0.88
    Night
    -0.75
     nights
    -0.74
     night
    -0.74
     Night
    -0.73
    night
    -0.71
     tonight
    -0.70
     Nights
    -0.70
    nights
    -0.69
     nighttime
    -0.69
    POSITIVE LOGITS
     lunch
    1.86
     Lunch
    1.67
    Lunch
    1.66
     noon
    1.62
     lunchtime
    1.58
    lunch
    1.56
     LUNCH
    1.54
     midday
    1.48
     afternoon
    1.34
     Noon
    1.34
    Activations Density 0.190%

    No Known Activations