© 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. 30-GEMMASCOPE-RES-16K
    11. 10900
    Prev
    Next
    INDEX
    Explanations

    references to teddy bears and associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    bears (including teddy bears)

    np_acts-logits-general · gemini-2.0-flash

    bear, teddy, Kuma, Polar, Ursa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.47
    帖最后由
    -0.42
    +#+#
    -0.40
    ########.
    -0.39
    tagHelperRunner
    -0.39
     transfieras
    -0.38
     rancho
    -0.37
     bolsillo
    -0.36
     Gogh
    -0.35
     Delft
    -0.34
    POSITIVE LOGITS
     bear
    2.11
     bears
    1.88
     Bear
    1.83
    bear
    1.79
    Bear
    1.75
     BEAR
    1.74
     Bears
    1.67
    bears
    1.57
    BEAR
    1.56
    🐻
    1.53
    Activations Density 0.105%

    No Known Activations