© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11699
    Prev
    Next
    INDEX
    Explanations

    terms associated with data transfer processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oogle
    -0.54
    cornerRadius
    -0.52
    Jîn
    -0.49
    onPage
    -0.49
     InputDecoration
    -0.49
     Opin
    -0.48
     onPage
    -0.48
    bgcolor
    -0.47
     Audience
    -0.47
    QFont
    -0.47
    POSITIVE LOGITS
     transfer
    2.03
     Transfer
    1.85
    transfer
    1.84
     transfers
    1.80
    Transfer
    1.76
     Transfers
    1.70
     TRANSFER
    1.69
     transfert
    1.56
     transferencia
    1.55
    Transfers
    1.53
    Activations Density 0.208%

    No Known Activations