© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35931
    Prev
    Next
    INDEX
    Explanations

    scientific terms and measurements related to chemical compounds

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

    health of, poor fibers, balance between

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects technical or domain-specific jargon — long, content-rich scientific/academic terms and specialized nouns.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -1.59
    Personendaten
    -1.33
    SourceChecksum
    -1.15
    featureID
    -1.05
     propOrder
    -1.02
     мәкал
    -1.00
    ➟
    -0.98
    :✨
    -0.97
    webElementXpaths
    -0.96
    Vidite
    -0.95
    POSITIVE LOGITS
     divino
    0.23
     gobern
    0.22
     \
    0.21
    \
    0.21
     […]
    0.21
     
    0.21
     kirke
    0.21
     bornes
    0.20
     trés
    0.20
     dorada
    0.20
    Activations Density 16.649%

    No Known Activations