© 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-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2580
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to medical research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.81
    Diweddarwch
    -0.65
    sizeCache
    -0.61
    tanleria
    -0.60
     pinulongan
    -0.57
    RenderAtEndOf
    -0.57
     صوتيه
    -0.57
     kaynağından
    -0.56
    twimg
    -0.54
    ſcher
    -0.54
    POSITIVE LOGITS
     Christiansen
    0.41
     Yoshida
    0.40
     Therefore
    0.39
     Tatsache
    0.39
     approach
    0.38
     particulières
    0.38
    Therefore
    0.38
     Hence
    0.37
     voisin
    0.37
     Eins
    0.36
    Activations Density 1.332%

    No Known Activations