© 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. 23011
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Климат
    -0.49
     geldig
    -0.46
     grunn
    -0.39
     mør
    -0.35
     mümkün
    -0.34
    droj
    -0.33
     lembran
    -0.33
    établissement
    -0.33
    next
    -0.33
     garrafa
    -0.32
    POSITIVE LOGITS
     disambiguazione
    3.52
    verwijspagina
    2.34
     ujednoznacz
    2.30
     sayfası
    2.14
    homonymie
    1.76
    niająca
    1.64
    曖昧さ回避
    1.18
    installer
    1.03
    página
    1.02
    rungsseite
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.