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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6315
    Prev
    Next
    INDEX
    Explanations

    references to server-related terminology and error codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     Kies
    -0.57
    RectangleBorder
    -0.56
    pick
    -0.52
    Pick
    -0.47
     Pik
    -0.47
     Pio
    -0.46
    Jody
    -0.46
     Pick
    -0.46
     Gusto
    -0.45
     QI
    -0.45
    POSITIVE LOGITS
     Server
    1.15
     server
    1.02
     SERVER
    1.01
    Server
    1.00
     Servers
    0.98
    getServer
    0.95
    SERVER
    0.88
    server
    0.86
     servidor
    0.86
     serveur
    0.84
    Activations Density 0.181%

    No Known Activations