© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13587
    Prev
    Next
    INDEX
    Explanations

    instances of the word "time" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.08
     myſelf
    -1.04
     doubtnut
    -1.00
     Theſe
    -0.96
     ſever
    -0.96
    ſelf
    -0.95
     Monfieur
    -0.95
     juſ
    -0.94
     fevere
    -0.93
     whoſe
    -0.93
    POSITIVE LOGITS
    time
    0.86
    times
    0.79
    piece
    0.77
    TIME
    0.71
     TIME
    0.69
    i
    0.69
     Time
    0.68
    tim
    0.68
    getTime
    0.67
    Time
    0.66
    Activations Density 0.124%

    No Known Activations