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. 5-GEMMASCOPE-RES-16K
    6. 4786
    Prev
    Next
    INDEX
    Explanations

    topics related to maintenance and service of equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.76
    rungsseite
    -0.71
    antity
    -0.62
    momix
    -0.62
     Permalink
    -0.62
    ьаж
    -0.61
    ITOS
    -0.61
    esterday
    -0.61
    
    -0.60
    Cyfeiriadau
    -0.60
    POSITIVE LOGITS
     maintenance
    1.30
     Maintenance
    1.08
    maintenance
    1.02
    Maintenance
    1.00
     MAINTENANCE
    0.97
     repairs
    0.86
     servicing
    0.86
     mainten
    0.84
     repair
    0.84
     upkeep
    0.84
    Activations Density 0.322%

    No Known Activations