© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7677
    Prev
    Next
    INDEX
    Explanations

    references to time periods and changes over time

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "[Time period] + ago/since"

    np_acts-logits-general · gemini-2.0-flash

    time periods and continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     recently
    -0.82
     currently
    -0.74
     recentemente
    -0.69
     recent
    -0.69
     recientemente
    -0.68
     kürzlich
    -0.67
    recently
    -0.64
     недавно
    -0.64
     presently
    -0.62
    currently
    -0.62
    POSITIVE LOGITS
     continuously
    0.88
     continually
    0.84
     consistently
    0.82
    我一直
    0.77
     steadily
    0.77
    一直在
    0.75
    陆续
    0.73
     constantly
    0.73
    不斷
    0.73
     kontinuier
    0.72
    Activations Density 0.408%

    No Known Activations