© 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. 4542
    Prev
    Next
    INDEX
    Explanations

    specific times of day associated with news broadcasts

    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
     lunch
    -0.73
     Lunch
    -0.71
    Lunch
    -0.68
     desay
    -0.65
     morning
    -0.64
    Morning
    -0.62
    上午
    -0.62
     brunch
    -0.61
     sunny
    -0.61
     Morning
    -0.61
    POSITIVE LOGITS
     tonight
    1.84
     evening
    1.83
    Tonight
    1.77
     Tonight
    1.71
    evening
    1.59
     nightly
    1.55
     night
    1.53
     evenings
    1.52
     Evening
    1.48
     Abend
    1.47
    Activations Density 0.262%

    No Known Activations