© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 94151
    Prev
    Next
    INDEX
    Explanations

    references to sleep and bedtime routines

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

    sleep and bedtime

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Бахар
    -0.47
    /**
    -0.46
     estekak
    -0.46
     resourceCulture
    -0.43
    multirow
    -0.42
    HeaderText
    -0.41
    TypedDataSet
    -0.40
    crata
    -0.40
    akai
    -0.39
    NameInMap
    -0.39
    POSITIVE LOGITS
     bedtime
    0.95
     sleep
    0.85
     night
    0.81
     nightly
    0.79
    Sleep
    0.77
     nighttime
    0.77
     SLEEP
    0.74
    night
    0.73
    Night
    0.73
     Sleep
    0.73
    Activations Density 0.077%

    No Known Activations