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

    Neuronpedia

    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. 3-GEMMASCOPE-RES-16K
    11. 13386
    Prev
    Next
    INDEX
    Explanations

    references to specific standards and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moulds
    -1.15
     licences
    -1.08
     metres
    -1.04
     fibres
    -1.02
     NSCoder
    -1.00
     artefacts
    -0.97
     tonnes
    -0.97
     moul
    -0.95
     Colours
    -0.95
    Colours
    -0.94
    POSITIVE LOGITS
     plz
    1.02
     EKG
    1.00
     disks
    0.98
     Polk
    0.97
     theaters
    0.95
     gages
    0.95
     theater
    0.94
     horaire
    0.92
     acrylique
    0.91
     cuz
    0.91
    Activations Density 3.495%

    No Known Activations