© 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. 3-GEMMASCOPE-RES-16K
    11. 4373
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or references to external stylesheets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     inmig
    -0.35
    audiovisuel
    -0.34
     procès
    -0.33
     Numerade
    -0.32
     Literary
    -0.32
     danni
    -0.32
     Trauer
    -0.32
     penghar
    -0.32
     embaj
    -0.32
     ropes
    -0.32
    POSITIVE LOGITS
     HILLS
    0.88
     rel
    0.85
     Hills
    0.84
    Hills
    0.79
    hills
    0.71
     Responsive
    0.71
     responsive
    0.70
     hills
    0.70
     Arena
    0.67
     arena
    0.66
    Activations Density 0.101%

    No Known Activations