© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10288
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sole"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     žem
    -0.53
    imageshack
    -0.50
     flèche
    -0.50
     Willis
    -0.48
     modelAndView
    -0.47
     pantallas
    -0.47
    MVP
    -0.47
    jsdelivr
    -0.46
     viva
    -0.46
     promesse
    -0.46
    POSITIVE LOGITS
     SOLE
    0.90
     الرياضيه
    0.87
    Personensuche
    0.85
    verwijspagina
    0.79
    دانشنامهٔ
    0.77
    曖昧さ回避
    0.76
    Sole
    0.75
    SOLE
    0.75
     Sole
    0.74
    Crypt
    0.74
    Activations Density 0.046%

    No Known Activations