© 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. 15726
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duration and time references in life experiences

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

    duration, period, or profession

    np_acts-logits-general · gemini-2.0-flash

    periods of time or duration

    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
    idać
    -0.36
    propTypes
    -0.36
    %")
    -0.34
     allgemeinen
    -0.33
     widok
    -0.33
     kıs
    -0.32
     miejsco
    -0.31
     Mitarbeitern
    -0.31
     collaborators
    -0.31
     mérite
    -0.30
    POSITIVE LOGITS
     tenure
    0.85
     lifetime
    0.75
     lifetimes
    0.74
     lifecycle
    0.73
     lifespan
    0.73
     career
    0.65
     autorytatywna
    0.64
     careers
    0.61
     nakalista
    0.61
     Lifecycle
    0.60
    Activations Density 0.432%

    No Known Activations