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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 10582
    Prev
    Next
    INDEX
    Explanations

    instances of the word "copy" and related programming or scripting functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Williams
    -0.73
     Goldman
    -0.68
    thane
    -0.66
    forums
    -0.66
     “
    -0.65
     ‘
    -0.65
     /\.(
    -0.64
     Wul
    -0.64
     Hawkins
    -0.62
     груди
    -0.61
    POSITIVE LOGITS
     copies
    1.60
     copy
    1.59
     Copies
    1.50
     COPY
    1.50
    copy
    1.45
     Copy
    1.39
    copies
    1.38
     COP
    1.35
     copying
    1.35
    COPY
    1.34
    Activations Density 0.107%

    No Known Activations