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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5139
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "produce" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    -0.64
     ainfi
    -0.60
     telefónica
    -0.58
     inalámb
    -0.56
    Mejores
    -0.54
     tibur
    -0.54
    jangkau
    -0.53
     cimetière
    -0.52
    farande
    -0.52
     revisión
    -0.52
    POSITIVE LOGITS
     produce
    1.02
    produce
    0.89
     Produce
    0.86
     production
    0.85
     produced
    0.84
     Produced
    0.80
    production
    0.80
     Produ
    0.77
     producer
    0.77
     produces
    0.76
    Activations Density 0.128%

    No Known Activations