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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16-GEMMASCOPE-RES-16K
    6. 11929
    Prev
    Next
    INDEX
    Explanations

    references to dental hygiene practices and maintenance

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

    Maintenance and care instructions

    np_acts-logits-general · gemini-2.0-flash

    care and upkeep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.65
    StoryboardSegue
    -0.57
    ıntı
    -0.53
     Markets
    -0.51
     táo
    -0.51
     ModelExpression
    -0.51
    IUrlHelper
    -0.50
     Schell
    -0.49
     prisonniers
    -0.49
    VideoCapture
    -0.48
    POSITIVE LOGITS
     upkeep
    0.98
     maintenance
    0.90
     care
    0.88
     caring
    0.77
    entretien
    0.77
    maintenance
    0.75
     Maintenance
    0.73
    Maintenance
    0.73
     cuidados
    0.72
     merawat
    0.71
    Activations Density 0.162%

    No Known Activations