© 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. 11-GEMMASCOPE-RES-16K
    6. 9206
    Prev
    Next
    INDEX
    Explanations

    enzymes and their biochemical properties related to reactions and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompag
    -0.43
     koszulka
    -0.43
     teşekkür
    -0.42
     adesivos
    -0.41
     kız
    -0.41
    ställning
    -0.41
     ragazza
    -0.41
    carteles
    -0.40
    vänt
    -0.40
    dziew
    -0.40
    POSITIVE LOGITS
     enzyme
    1.17
     enzymes
    1.08
     Enzyme
    1.05
     Enzymes
    1.04
    enzyme
    1.04
     enzy
    1.02
    Enzyme
    0.98
     enzymatic
    0.94
    zymes
    0.89
    zyme
    0.88
    Activations Density 1.347%

    No Known Activations