© 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. 12-GEMMASCOPE-RES-16K
    11. 13906
    Prev
    Next
    INDEX
    Explanations

    patterns and data related to collective or overarching themes and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.60
    Хьажоргаш
    -0.42
     Disposal
    -0.38
     Unle
    -0.38
     voire
    -0.38
    ologue
    -0.37
    某
    -0.37
     saites
    -0.37
    lessed
    -0.37
     something
    -0.37
    POSITIVE LOGITS
     Semua
    0.68
     everything
    0.67
     모든
    0.66
     wszystkie
    0.62
    的一切
    0.60
     всички
    0.60
    Semua
    0.60
    everything
    0.60
     todas
    0.60
    全ての
    0.59
    Activations Density 1.218%

    No Known Activations