© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1822
    Prev
    Next
    INDEX
    Explanations

    medical terms and descriptions related to patient assessments and surgical procedures

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

    "[Impaired/decreased] [bodily function]"

    np_acts-logits-general · gemini-2.0-flash

    impaired and preserved function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.69
     raiſ
    -0.66
     ſte
    -0.66
    cos
    -0.65
    AutoScaleMode
    -0.63
     Jefus
    -0.63
     caufe
    -0.63
     neceff
    -0.62
    HostException
    -0.62
     myſelf
    -0.61
    POSITIVE LOGITS
     functioning
    0.85
     functionality
    0.79
    functioning
    0.78
     function
    0.78
     functional
    0.77
     Function
    0.68
    Functionality
    0.68
     ability
    0.67
     FUNCTION
    0.64
    function
    0.64
    Activations Density 0.689%

    No Known Activations