© 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. 2-GEMMASCOPE-RES-16K
    11. 3545
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sitting."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hjælp
    -0.49
     retenir
    -0.48
     vyu
    -0.47
     tæ
    -0.44
     stället
    -0.43
     håll
    -0.42
    voerd
    -0.41
    fø
    -0.41
     hjelp
    -0.41
     Whence
    -0.41
    POSITIVE LOGITS
     sitting
    2.23
    sitting
    1.84
     Sitting
    1.84
    Sitting
    1.80
     lying
    1.79
     standing
    1.66
     hanging
    1.62
     Lying
    1.38
     Hanging
    1.34
    Lying
    1.30
    Activations Density 0.150%

    No Known Activations