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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114591
    Prev
    Next
    INDEX
    Explanations

    references to infrastructure and facilities related to transportation and utilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     defaultstate
    -0.79
     unknownFields
    -0.57
    oredCriteria
    -0.56
    
    -0.54
    styleType
    -0.54
    greenrobot
    -0.53
     MainAxisSize
    -0.51
    msgSender
    -0.49
     pinulongan
    -0.49
    WriteTagHelper
    -0.49
    POSITIVE LOGITS
     Meksiku
    0.43
     Miniature
    0.40
     diminutive
    0.39
    petite
    0.39
     arşivlendi
    0.38
    ▌
    0.37
     kecil
    0.36
     mini
    0.36
     fhort
    0.36
    ,
    
    
    0.36
    Activations Density 0.124%

    No Known Activations