Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 30486
    Prev
    Next
    INDEX
    Explanations

    specific nouns and terms related to various fields, including medicine, physics, and multimedia

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

    domain specific phrases

    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
     Wohnungen
    -0.64
     Öffnungszeiten
    -0.59
     Absicht
    -0.57
     inmediata
    -0.56
     rumahnya
    -0.56
     autorité
    -0.56
     poszczegól
    -0.56
     peraturan
    -0.55
     esperança
    -0.55
     Verhandlungen
    -0.54
    POSITIVE LOGITS
     ſte
    0.75
     ſta
    0.71
     surla
    0.70
     tartalomajánló
    0.69
     carto
    0.68
     Patro
    0.66
    ChildScrollView
    0.66
     multil
    0.66
    IVEREF
    0.65
     digi
    0.65
    Activations Density 0.413%

    No Known Activations