© 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. 31200
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases indicating actions, roles, and features within various contexts

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

    ceased, reduced, or completed

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Aufklärung
    -0.42
    Élet
    -0.41
     jeweiligen
    -0.40
    Referenties
    -0.39
     Verarbeitung
    -0.38
     Begegn
    -0.38
     jeweils
    -0.38
     Hoffnung
    -0.36
    Rozm
    -0.36
     bohater
    -0.35
    POSITIVE LOGITS
     EconPapers
    0.67
     незавершена
    0.66
     للمعارف
    0.66
    TagMode
    0.66
     kiệm
    0.60
    lccn
    0.59
     lccn
    0.58
    Tembelea
    0.58
     AssemblyVersion
    0.57
    المناصب
    0.56
    Activations Density 0.089%

    No Known Activations