© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11872
    Prev
    Next
    INDEX
    Explanations

    references to time durations and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to time periods measured in months, especially phrases like "six months" or "period of X months."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rosa
    -0.38
     Menu
    -0.36
     menu
    -0.34
     عصر
    -0.33
    menu
    -0.32
     bł
    -0.32
     czyn
    -0.32
    Menu
    -0.32
     tinggi
    -0.31
    rowsiness
    -0.31
    POSITIVE LOGITS
     months
    0.84
    Months
    0.80
     Months
    0.77
    months
    0.76
     MONTHS
    0.68
     månader
    0.66
     maanden
    0.66
    parsedMessage
    0.64
     Monaten
    0.61
     meses
    0.59
    Activations Density 0.288%

    No Known Activations