© 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. 18-GEMMASCOPE-RES-16K
    6. 7182
    Prev
    Next
    INDEX
    Explanations

    terms related to enzymatic activity and metabolism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    enzymes and enzymatic activity

    np_acts-logits-general · gemini-2.0-flash

    enzyme activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     owner
    -0.47
     propriétaire
    -0.46
     Krie
    -0.46
    kunde
    -0.45
     ved
    -0.43
    naut
    -0.43
    itemize
    -0.43
     repel
    -0.42
    ElementException
    -0.41
     ska
    -0.41
    POSITIVE LOGITS
     enzyme
    1.46
     enzymes
    1.34
     enzymatic
    1.30
     enzy
    1.26
     Enzyme
    1.25
     Enzymes
    1.17
     catalytic
    1.14
     Enzy
    1.09
    enzyme
    1.08
    Enzyme
    1.07
    Activations Density 1.200%

    No Known Activations