© 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. 37-GEMMASCOPE-RES-16K
    11. 6409
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically days of the week and scheduling

    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
     فريبيس
    -0.79
    TagMode
    -0.66
    LookAnd
    -0.55
    ValueStyle
    -0.54
     صوتيه
    -0.52
    saraba
    -0.52
     intptr
    -0.52
    KURZBESCHREIBUNG
    -0.51
    CPtr
    -0.49
     <<<<<<<<<<<<<<
    -0.48
    POSITIVE LOGITS
     week
    2.94
    week
    2.41
     Week
    2.39
    Week
    2.30
     WEEK
    2.19
     Woche
    1.99
     semana
    1.98
    WEEK
    1.94
     semaine
    1.92
     weeks
    1.84
    Activations Density 0.570%

    No Known Activations