© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 5578
    Prev
    Next
    INDEX
    Explanations

    references to "copy" and related operations in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    complexContent
    -0.90
    uxxxx
    -0.76
     MenuView
    -0.65
    StoryboardSegue
    -0.64
     unknownFields
    -0.63
     TestBed
    -0.62
    textTheme
    -0.62
     betweenstory
    -0.60
    SdkVersion
    -0.58
     /\.(
    -0.58
    POSITIVE LOGITS
     paste
    1.07
     Paste
    0.94
    Paste
    0.89
     pasting
    0.88
     copies
    0.85
     pasted
    0.83
     copy
    0.81
     Copy
    0.81
     COPY
    0.80
     COP
    0.79
    Activations Density 0.105%

    No Known Activations