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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8563
    Prev
    Next
    INDEX
    Explanations

    control flow structures and conditions in programming code

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     CommonModule
    -0.64
    richTextPanel
    -0.64
    verwijspagina
    -0.63
    PerformLayout
    -0.62
     resourceCulture
    -0.60
    tonode
    -0.57
    bufio
    -0.57
    webElementXpaths
    -0.57
    脚注の使い方
    -0.57
    :✨
    -0.56
    POSITIVE LOGITS
     typelib
    0.44
    "))
    
    0.40
     seines
    0.39
    UseVisualStyle
    0.39
    因而
    0.38
    )))
    
    0.37
     Pingback
    0.37
     ""))
    0.37
     progressively
    0.36
    '))
    
    0.36
    Activations Density 0.065%

    No Known Activations