© 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. 13-GEMMASCOPE-RES-16K
    11. 6003
    Prev
    Next
    INDEX
    Explanations

    text related to copyright and copying software or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esgue
    -0.54
    getStatus
    -0.54
     Sart
    -0.50
     Mead
    -0.48
     HttpStatus
    -0.48
     Chic
    -0.48
    extAlignment
    -0.47
     Kerr
    -0.46
     Variables
    -0.46
    Искәрмәләр
    -0.45
    POSITIVE LOGITS
     copy
    1.70
    copy
    1.49
    Copy
    1.47
     copies
    1.46
     Copy
    1.41
     COPY
    1.38
    COPY
    1.30
     copie
    1.24
    copies
    1.23
     Copies
    1.23
    Activations Density 0.168%

    No Known Activations