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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7070
    Prev
    Next
    INDEX
    Explanations

    repetitive use of the word "just" and its various forms in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comunicaciones
    -0.54
     rozwój
    -0.53
     wyposa
    -0.52
     ennemis
    -0.51
     společnosti
    -0.50
     aikana
    -0.49
    enciaga
    -0.48
     bezpieczeństwa
    -0.47
    hosa
    -0.45
     gedrag
    -0.45
    POSITIVE LOGITS
     JUST
    1.01
    just
    0.98
     Just
    0.90
     just
    0.90
    Just
    0.89
    JUST
    0.83
     Просто
    0.68
    Просто
    0.63
    addGap
    0.62
     просто
    0.60
    Activations Density 0.096%

    No Known Activations