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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 5086
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing maintenance and restoration activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.81
     Efq
    -0.76
    fromnode
    -0.76
     myſelf
    -0.74
     pleaſure
    -0.74
     MainAxisSize
    -0.73
     وتسجيلات
    -0.73
     himſelf
    -0.73
    StoryboardSegue
    -0.72
     resourceCulture
    -0.71
    POSITIVE LOGITS
     repair
    0.86
     repairs
    0.82
     refurb
    0.74
     Repair
    0.74
    repair
    0.70
     renovation
    0.67
     re
    0.67
     ремонт
    0.66
    Repair
    0.64
     renovations
    0.63
    Activations Density 0.170%

    No Known Activations