© 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. 2-GEMMASCOPE-RES-16K
    11. 9484
    Prev
    Next
    INDEX
    Explanations

    mentions of weeks, particularly focusing on the concept of "week" as it relates to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Daylight
    -0.49
    daylight
    -0.40
     gebo
    -0.39
     فريبيس
    -0.37
    DBNull
    -0.36
     daylight
    -0.36
    utilisons
    -0.35
    testify
    -0.34
    CPtr
    -0.34
    astéroïdes
    -0.34
    POSITIVE LOGITS
     week
    3.73
    Week
    3.53
     Week
    3.52
    week
    3.41
     WEEK
    3.28
    WEEK
    2.94
     semana
    2.72
     Woche
    2.59
     semaine
    2.48
     weeks
    2.31
    Activations Density 0.084%

    No Known Activations