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. 13923
    Prev
    Next
    INDEX
    Explanations

    references to celebrations and community events

    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
    ScopeManager
    -0.69
    TagMode
    -0.61
     whiteboard
    -0.54
    شهاد
    -0.54
     label
    -0.53
    StoryboardSegue
    -0.53
     monasterio
    -0.52
     Facility
    -0.50
     studio
    -0.50
    ьаж
    -0.50
    POSITIVE LOGITS
     parade
    1.65
     parades
    1.49
     Parade
    1.31
    parade
    1.29
     procession
    1.25
    Parade
    1.20
     processions
    1.14
     marching
    1.13
     desfile
    1.12
     fireworks
    1.02
    Activations Density 0.157%

    No Known Activations