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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6191
    Prev
    Next
    INDEX
    Explanations

    medical measurements and parameters related to patient assessments

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

    Positions of people or patients

    np_acts-logits-general · gemini-2.0-flash

    describing body positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighborhood
    -0.49
    eaways
    -0.48
    JMenu
    -0.45
    phens
    -0.45
    oughs
    -0.44
    tempered
    -0.43
     encode
    -0.43
     Италијани
    -0.43
     coded
    -0.42
    tider
    -0.42
    POSITIVE LOGITS
     sitting
    2.00
     standing
    1.94
    sitting
    1.71
     Sitting
    1.69
     sit
    1.69
     seated
    1.66
     Standing
    1.66
    Standing
    1.64
    Sitting
    1.63
     sits
    1.53
    Activations Density 0.480%

    No Known Activations