© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7761
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and outcomes in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Appellants
    -0.71
    Apar
    -0.66
    Adv
    -0.66
    Atta
    -0.66
    Amen
    -0.65
    tangentMode
    -0.65
    Alco
    -0.64
    Adm
    -0.64
    ADV
    -0.64
    adv
    -0.64
    POSITIVE LOGITS
    épaisseur
    1.03
    hygiène
    0.90
    extrême
    0.86
    amitié
    0.85
    échelle
    0.84
    enfance
    0.82
    humanité
    0.81
    automne
    0.79
    empêcher
    0.79
    éclairage
    0.78
    Activations Density 2.822%

    No Known Activations