© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 9457
    Prev
    Next
    INDEX
    Explanations

    instances of people sitting down or engaging in seated activities

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

    the action of sitting

    np_acts-logits-general · gemini-2.0-flash

    forms of sit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     declaration
    -0.49
     Declaration
    -0.48
    decke
    -0.46
     DECLARATION
    -0.45
    jaman
    -0.43
     declarations
    -0.42
     National
    -0.42
    trui
    -0.41
     تضيفلها
    -0.41
    gaard
    -0.41
    POSITIVE LOGITS
    Sit
    1.01
     sit
    1.00
     Sit
    0.93
     sitting
    0.90
    Sitting
    0.86
     sits
    0.83
    sit
    0.82
     Sitting
    0.82
    sitting
    0.78
     sat
    0.77
    Activations Density 0.116%

    No Known Activations