Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 16091
    Prev
    Next
    INDEX
    Explanations

    instances of the word "run" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gezegd
    -0.80
     Southgate
    -0.80
     Northampton
    -0.78
     Bez
    -0.78
     Tomlinson
    -0.77
     Oester
    -0.76
     Peers
    -0.75
    valents
    -0.74
     Colchester
    -0.74
     EGL
    -0.74
    POSITIVE LOGITS
     run
    2.18
     runs
    2.01
     running
    1.98
     Run
    1.94
    run
    1.90
    Run
    1.86
     RUN
    1.83
     ran
    1.82
     Running
    1.81
    running
    1.80
    Activations Density 0.055%

    No Known Activations