© 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. 15746
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "run" and its variations in different contexts

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

    the word "run" (and its variants)

    np_acts-logits-general · gemini-2.0-flash

    running out

    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
    IUrlHelper
    -0.44
     disambiguazione
    -0.42
    참고
    -0.38
    ercizi
    -0.37
     Numerade
    -0.36
    oltà
    -0.36
    ModelAttribute
    -0.35
    alain
    -0.35
    éric
    -0.34
    +#+
    -0.34
    POSITIVE LOGITS
     run
    1.07
     Run
    1.07
     RUN
    1.06
     Running
    1.05
    run
    1.00
    running
    0.99
    Running
    0.98
    Run
    0.97
    RUN
    0.96
     RUNNING
    0.96
    Activations Density 0.135%

    No Known Activations