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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 5979
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "copy" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roc
    -0.52
    async
    -0.50
    Bos
    -0.48
    brio
    -0.47
    期刊论文
    -0.46
    Emerging
    -0.46
    NM
    -0.45
    inema
    -0.45
    Common
    -0.45
    heiro
    -0.45
    POSITIVE LOGITS
     duplicate
    1.34
     copied
    1.25
     copy
    1.24
     Duplicate
    1.13
     duplicated
    1.05
     copying
    1.05
     copies
    1.03
     duplicates
    1.03
    copied
    1.02
     Copy
    0.97
    Activations Density 0.891%

    No Known Activations