© 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. 9003
    Prev
    Next
    INDEX
    Explanations

    references to specific cards in events or lists

    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
     ddelweddau
    -0.60
     recul
    -0.55
     préférence
    -0.52
    cox
    -0.50
    gameserver
    -0.49
    intellij
    -0.48
    adona
    -0.48
     vroeg
    -0.48
    хьтан
    -0.46
     Dato
    -0.46
    POSITIVE LOGITS
     بيها
    0.84
     roster
    0.84
     checklist
    0.82
     للمعارف
    0.79
     shelf
    0.75
     scoreboard
    0.75
     hierarchy
    0.74
     lineup
    0.73
    AccessorTable
    0.72
     <>",
    0.72
    Activations Density 1.327%

    No Known Activations