© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7173
    Prev
    Next
    INDEX
    Explanations

    references to time and sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Days
    -1.00
    Days
    -0.96
    DAYS
    -0.91
     DAYS
    -0.84
    days
    -0.78
     Nights
    -0.75
    nights
    -0.71
    Nights
    -0.69
    Weeks
    -0.67
    Week
    -0.65
    POSITIVE LOGITS
     morning
    0.70
     day
    0.61
     say
    0.56
     morm
    0.54
     mor
    0.53
    MemoryWarning
    0.52
     arvo
    0.50
    UnusedPrivate
    0.48
     afternoon
    0.47
     fay
    0.47
    Activations Density 0.201%

    No Known Activations