© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11026
    Prev
    Next
    INDEX
    Explanations

    references to blogging and related community topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eléct
    -0.37
     asisten
    -0.35
     parís
    -0.34
     ſur
    -0.33
     représentation
    -0.32
     sép
    -0.32
     crí
    -0.32
     fís
    -0.31
     méri
    -0.30
     ſa
    -0.29
    POSITIVE LOGITS
    geddon
    0.80
     dudes
    0.75
     дописавши
    0.73
     >=",
    0.71
    licious
    0.70
     dude
    0.70
     mania
    0.70
     vibes
    0.69
     mojo
    0.69
     apocalypse
    0.68
    Activations Density 0.606%

    No Known Activations