© 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. 11-GEMMASCOPE-RES-16K
    11. 5259
    Prev
    Next
    INDEX
    Explanations

    names and affiliations related to research funding or authorship

    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
     zelve
    -0.56
     gekomen
    -0.50
     gevo
    -0.48
     dezelve
    -0.46
     zichzelf
    -0.45
     betaal
    -0.43
     groter
    -0.42
     mijne
    -0.42
     zijne
    -0.42
     vermeld
    -0.42
    POSITIVE LOGITS
     Dutch
    0.74
     dutch
    0.70
     holand
    0.68
    Dutch
    0.67
     pinulongan
    0.65
    liceerd
    0.62
     Delft
    0.61
    荷兰
    0.61
     Netherlands
    0.60
     HasFactory
    0.59
    Activations Density 1.041%

    No Known Activations