© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1806
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and duration in the context of financial debt management

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

    in a span of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     متعلقه
    -0.77
    脚注の使い方
    -0.74
     arşivlendi
    -0.73
     للمعارف
    -0.73
    MemoryWarning
    -0.72
    
    -0.72
    TemporalType
    -0.72
    TagMode
    -0.71
     незавершена
    -0.71
    #
    -0.70
    POSITIVE LOGITS
     less
    1.17
    Less
    0.90
     Less
    0.86
     menos
    0.82
     LESS
    0.82
     lefs
    0.81
     leſs
    0.81
     moins
    0.80
     minutes
    0.78
     fewer
    0.78
    Activations Density 0.082%

    No Known Activations