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. 21-GEMMASCOPE-RES-16K
    6. 7417
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /\.(
    -0.65
     /\.
    -0.63
     AssemblyVersion
    -0.62
    GraphicsUnit
    -0.60
    際には
    -0.57
    ThroughAttribute
    -0.57
    brigens
    -0.56
     nahilalakip
    -0.54
    SuppressMessage
    -0.53
     useSelector
    -0.51
    POSITIVE LOGITS
     sitting
    1.25
    Sitting
    1.15
     sit
    1.14
    sitting
    1.10
     Sitting
    1.09
     sat
    1.09
     sits
    0.99
     walked
    0.95
     walking
    0.93
     sentado
    0.93
    Activations Density 0.365%

    No Known Activations