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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7548
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs, particularly related to date and time operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     pleaſure
    -1.00
     GenerationType
    -0.91
     оригіналу
    -0.89
     reaſon
    -0.88
     purpoſe
    -0.87
     themſelves
    -0.85
     himſelf
    -0.83
     myſelf
    -0.82
    RUnlock
    -0.81
     Majefty
    -0.80
    POSITIVE LOGITS
    "]))
    0.61
    ")));
    
    0.56
     my
    0.55
    ")]
    
    0.55
    ']))
    0.53
    "));
    
    0.51
    PENT
    0.50
     c
    0.50
    ")[
    0.50
    "){
    
    0.50
    Activations Density 0.105%

    No Known Activations