© 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. 15-GEMMASCOPE-RES-16K
    6. 6202
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Today" and variations in tense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nestjs
    -0.83
     AC
    -0.66
    følgelig
    -0.62
    al
    -0.62
    Sk
    -0.61
    ValueGenerated
    -0.61
     Ross
    -0.61
    ë
    -0.61
     Berk
    -0.60
    cs
    -0.59
    POSITIVE LOGITS
     Oggi
    1.18
     TODAY
    1.17
    TODAY
    1.15
     Today
    1.14
     Hoje
    1.13
    andaag
    1.11
     todays
    1.08
    Today
    1.07
     Aujourd
    1.06
    today
    1.06
    Activations Density 0.048%

    No Known Activations