© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9605
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically centuries and decades, along with related historical contexts

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

    decade abbreviations and references to time periods (e.g., '50s, '60s, '70s, '80s, '90s, 15th century, 16th-17th centuries, 1980s, 1970s, twentieth century).

    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
    ingtones
    -0.50
    liceerd
    -0.50
    MessageTagHelper
    -0.49
     yyr
    -0.48
    ftest
    -0.45
    祈
    -0.45
    medriver
    -0.45
    sweetalert
    -0.44
    DispatchToProps
    -0.44
     tham
    -0.44
    POSITIVE LOGITS
     era
    0.60
     Era
    0.52
    Era
    0.51
     onwards
    0.50
     Suomessa
    0.48
    InjectAttribute
    0.47
     boyunca
    0.46
     dönem
    0.45
     میل
    0.45
    突入
    0.44
    Activations Density 0.252%

    No Known Activations