© 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. 12-GEMMASCOPE-RES-16K
    11. 7877
    Prev
    Next
    INDEX
    Explanations

    references to time durations and intervals

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

    time duration expressions, particularly the word "hours" and surrounding context related to temporal measurements.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     rege
    -0.40
    widetilde
    -0.39
     APPLICABLE
    -0.38
     relever
    -0.37
    keda
    -0.37
    itic
    -0.36
    chtenstein
    -0.36
     Pflanze
    -0.35
    siapkan
    -0.35
    tende
    -0.35
    POSITIVE LOGITS
     Hour
    1.68
    Hour
    1.62
     Hours
    1.56
     hours
    1.51
     HOUR
    1.48
    Hours
    1.48
    hours
    1.47
    hour
    1.45
     hour
    1.45
    HOUR
    1.40
    Activations Density 0.128%

    No Known Activations