© 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. 0-GEMMASCOPE-RES-16K
    11. 7868
    Prev
    Next
    INDEX
    Explanations

    terms related to packaging and the word "pack."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цезда
    -0.40
     незавершена
    -0.39
     terdekat
    -0.38
    Gweler
    -0.38
     desierto
    -0.37
    EditorBrowsable
    -0.34
    ͝
    -0.34
     vœ
    -0.33
     medidor
    -0.33
     Jérusalem
    -0.33
    POSITIVE LOGITS
     package
    3.03
     pack
    2.95
     PACK
    2.94
     Pack
    2.88
     Package
    2.86
     packages
    2.84
    pack
    2.69
     packs
    2.67
     Packages
    2.66
    Pack
    2.64
    Activations Density 0.162%

    No Known Activations