© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10963
    Prev
    Next
    INDEX
    Explanations

    references to days of the week and weekends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ništvo
    -0.59
    sidemargin
    -0.50
     tute
    -0.50
    ransition
    -0.49
    ۞
    -0.48
     transitioned
    -0.48
    casio
    -0.48
    plish
    -0.48
    racht
    -0.48
     Schmitt
    -0.48
    POSITIVE LOGITS
     weekend
    1.35
     Sunday
    1.27
    Sunday
    1.25
    weekend
    1.22
     SUNDAY
    1.18
     Saturday
    1.15
    Weekend
    1.14
    Saturday
    1.13
     Weekend
    1.12
     sunday
    1.09
    Activations Density 0.139%

    No Known Activations