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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4386
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "run" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.86
     EGL
    -0.85
     Oester
    -0.82
     myſelf
    -0.82
     Southgate
    -0.81
     Northampton
    -0.81
     magistrates
    -0.80
     Magda
    -0.80
    tvguidetime
    -0.79
     Colchester
    -0.78
    POSITIVE LOGITS
     run
    1.74
     Run
    1.59
     runs
    1.57
     RUN
    1.56
    run
    1.55
    Run
    1.50
    RUN
    1.48
     Runs
    1.45
    RunWith
    1.41
    runs
    1.41
    Activations Density 0.071%

    No Known Activations