Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7674
    Prev
    Next
    INDEX
    Explanations

    references to therapeutic techniques and treatments in health and fitness contexts

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

    Alternative therapies or medical treatments

    np_acts-logits-general · gemini-2.0-flash

    medical therapies and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.69
     vuitton
    -0.68
    dymyr
    -0.68
     raiſ
    -0.68
     Meteorological
    -0.65
    ValueStyle
    -0.65
    ########.
    -0.65
    httphttps
    -0.64
     poffible
    -0.64
     poffe
    -0.64
    POSITIVE LOGITS
     chiropractic
    0.89
     Chiropractic
    0.84
     massage
    0.74
     rehab
    0.71
     acupuncture
    0.70
    ropractor
    0.69
     rehabilit
    0.68
     Massage
    0.65
     kines
    0.65
     Acupuncture
    0.64
    Activations Density 0.251%

    No Known Activations