© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 9518
    Prev
    Next
    INDEX
    Explanations

    terms related to adrenal hormones and their effects on physiological responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trasparente
    -0.57
     sandalias
    -0.52
     sélectionnés
    -0.50
     cover
    -0.50
    Last
    -0.50
     self
    -0.49
    Self
    -0.49
     Last
    -0.49
     spéciaux
    -0.48
     last
    -0.47
    POSITIVE LOGITS
     adrenaline
    0.90
     propOrder
    0.80
    ArrowToggle
    0.73
     Caffeine
    0.71
     stimulants
    0.70
    IntoConstraints
    0.69
    IUrlHelper
    0.68
     chi̍t
    0.68
     invokingState
    0.68
    цездатний
    0.66
    Activations Density 1.776%

    No Known Activations