© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 115454
    Prev
    Next
    INDEX
    Explanations

    instances of the word "produce" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    producing results or outputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Atlántico
    -0.60
    Neighbors
    -0.57
    farande
    -0.54
    onedDateTime
    -0.53
     telefónica
    -0.52
     inalámb
    -0.51
     איך
    -0.51
     Kowalski
    -0.50
     étro
    -0.49
     habitudes
    -0.49
    POSITIVE LOGITS
     produce
    1.09
    produce
    0.98
     Produce
    0.93
     produced
    0.88
    Produces
    0.86
    Produce
    0.85
     produces
    0.84
     Produced
    0.80
    produced
    0.78
    produces
    0.73
    Activations Density 0.050%

    No Known Activations