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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7482
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to data processing and manipulation in programming, specifically involving key-value pairs and transformations in data sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    SaveChanges
    -0.42
    baomidou
    -0.33
     pop
    -0.32
     šte
    -0.30
     Fieber
    -0.30
     tink
    -0.29
     Mexiko
    -0.29
    Pop
    -0.28
     helped
    -0.27
     fogo
    -0.27
    POSITIVE LOGITS
    Writable
    0.94
    Personendaten
    0.90
     незавершена
    0.71
    
    0.65
     الرياضيه
    0.63
    WaitGroup
    0.63
     getItemId
    0.61
    addCriterion
    0.61
     Writ
    0.61
    HtmlAttribute
    0.59
    Activations Density 0.001%

    No Known Activations