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. 15436
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court processes and orders

    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
     flavorful
    -0.66
    favorite
    -0.65
    Enrollment
    -0.61
    FAVOR
    -0.61
     favorite
    -0.61
    Favorite
    -0.59
    Neighbors
    -0.59
     neighboring
    -0.57
     favors
    -0.56
     neighbors
    -0.56
    POSITIVE LOGITS
    
    1.11
     Australian
    1.07
     Queensland
    1.01
    Australian
    1.00
     Australia
    1.00
     Melbourne
    0.95
     Pty
    0.94
     Australians
    0.93
     NSW
    0.93
     Australien
    0.92
    Activations Density 0.776%

    No Known Activations