© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1775
    Prev
    Next
    INDEX
    Explanations

    terms related to financial penalties and auditing practices

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

    banking and airlines

    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
    AndEndTag
    -0.78
    sizeCache
    -0.70
    tagHelperRunner
    -0.67
    COLN
    -0.64
    BagLayout
    -0.64
    例文帳に追加
    -0.61
     незавершена
    -0.60
    ListItemIcon
    -0.57
    transQ
    -0.56
    HomeAsUp
    -0.56
    POSITIVE LOGITS
     banking
    0.94
     airline
    0.91
     Bank
    0.87
     bank
    0.84
     Banking
    0.81
     telecom
    0.79
     Airlines
    0.79
     pharmaceutical
    0.78
     Airline
    0.78
     airlines
    0.78
    Activations Density 0.223%

    No Known Activations