© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5392
    Prev
    Next
    INDEX
    Explanations

    terms related to physical therapy and rehabilitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indu
    -0.49
     nahilalakip
    -0.47
    LookAnd
    -0.47
    Jereo
    -0.44
    itattu
    -0.44
     dAtA
    -0.43
     induk
    -0.42
    radura
    -0.41
     ExecuteAsync
    -0.41
     indu
    -0.41
    POSITIVE LOGITS
     physiotherapy
    0.72
     Rehabilitation
    0.70
     rehabilitation
    0.66
     Rehab
    0.66
     therapist
    0.64
     therapists
    0.64
     Therap
    0.63
     therapy
    0.63
    Therapy
    0.63
     rehab
    0.63
    Activations Density 0.529%

    No Known Activations