© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 98919
    Prev
    Next
    INDEX
    Explanations

    the presence of specific software library references and related terminologies

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

    transition, nanoparticles, Sithon, seventyfive, unusual

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

    The neuron detects tokens characteristic of formal scientific/technical documents and document structure—headings, citations/proper nouns, and domain-specific technical terms.

    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
    principalTable
    -0.60
     ivelany
    -0.55
     ostavi
    -0.55
    Билгалдахарш
    -0.51
     Roskov
    -0.51
     Administrativna
    -0.50
     kaarangay
    -0.48
     otomatig
    -0.48
     мәкалә
    -0.48
     ویکی‌آمباردا
    -0.47
    POSITIVE LOGITS
    原始内容存档于
    0.48
    sizeCache
    0.43
    ModelMap
    0.36
    principalColumn
    0.35
    ISupport
    0.35
    dataclass
    0.35
    prepareStatement
    0.34
    ToAction
    0.33
     Western
    0.32
    wester
    0.32
    Activations Density 0.564%

    No Known Activations