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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15575
    Prev
    Next
    INDEX
    Explanations

    references to health issues, specifically related to the elderly and community-dwelling adults

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

    aging or older people

    np_acts-logits-general · gemini-2.0-flash

    elderly and aging

    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
    Искәрмәләр
    -0.50
    ivore
    -0.49
    èvement
    -0.48
    glTexCoord
    -0.46
    InitVars
    -0.45
     cocaína
    -0.45
    ENESS
    -0.44
    +#+#
    -0.43
    EndInit
    -0.43
     Fant
    -0.43
    POSITIVE LOGITS
     elderly
    2.08
     aging
    1.96
     retirement
    1.91
     ageing
    1.86
     Elderly
    1.85
     retired
    1.84
     Aging
    1.82
     retirees
    1.80
     seniors
    1.74
     Retired
    1.72
    Activations Density 0.486%

    No Known Activations