© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8187
    Prev
    Next
    INDEX
    Explanations

    time references related to midnight and late-night activities

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

    Times of day (especially around midnight)

    np_acts-logits-general · gemini-2.0-flash

    specific clock times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     steg
    -0.40
    URLException
    -0.39
     lizenzfreies
    -0.38
     بيها
    -0.38
    发表于
    -0.38
     ✭✭
    -0.38
    CardHeader
    -0.36
    ItemBackground
    -0.35
     betweenstory
    -0.35
    complexContent
    -0.35
    POSITIVE LOGITS
     midnight
    1.09
    midnight
    1.04
    Midnight
    0.98
     Midnight
    0.94
     notte
    0.57
    Noct
    0.57
     natten
    0.57
     madrugada
    0.56
     nocy
    0.55
    深夜
    0.54
    Activations Density 0.249%

    No Known Activations