© 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
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12747
    Prev
    Next
    INDEX
    Explanations

    instances of the word "copy" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.45
    ָׁ
    -0.40
    Referências
    -0.37
    esgue
    -0.35
    hre
    -0.34
    WebServlet
    -0.34
    audrait
    -0.33
     мі
    -0.33
     Hines
    -0.33
     getName
    -0.32
    POSITIVE LOGITS
     copy
    4.31
    copy
    3.97
     Copy
    3.92
    Copy
    3.81
     COPY
    3.48
     copies
    3.34
    COPY
    3.23
     copying
    3.09
     copied
    3.06
     Copies
    2.95
    Activations Density 0.223%

    No Known Activations