© 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. 31-GEMMASCOPE-RES-16K
    6. 3882
    Prev
    Next
    INDEX
    Explanations

    quantifiable durations or time periods related to legal sentences or statutory limits

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

    numerical quantities, especially in the form of numbers followed by units like years, days, weeks, or percentages.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.37
    Almost
    -0.36
    cluso
    -0.35
    Autoritní
    -0.35
    including
    -0.35
     nakalista
    -0.35
    giarism
    -0.33
    almost
    -0.32
    ността
    -0.32
     걸
    -0.31
    POSITIVE LOGITS
    httphttps
    0.68
    Попис
    0.61
     faſt
    0.61
    $\%$
    0.59
     samti
    0.57
    
    0.56
     depositphotos
    0.56
     consecutive
    0.55
    éez
    0.54
     незавершена
    0.54
    Activations Density 0.798%

    No Known Activations