© 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. 1-GEMMASCOPE-RES-16K
    11. 10235
    Prev
    Next
    INDEX
    Explanations

    terms related to nutritional deficiencies and the impact of insufficient nutrients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrBuilder
    -0.66
    Viited
    -0.62
    dymyr
    -0.59
    consulté
    -0.55
    bkz
    -0.52
     bets
    -0.50
     שוליים
    -0.49
    esgue
    -0.49
     καν
    -0.49
     חיצוניים
    -0.49
    POSITIVE LOGITS
     deficiency
    2.94
     deficiencies
    2.83
     Deficiency
    2.50
     deficient
    2.42
     shortage
    2.33
     Defic
    2.24
     lacking
    2.16
     shortcomings
    2.14
     lack
    2.13
     deficit
    2.11
    Activations Density 0.204%

    No Known Activations