© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12845
    Prev
    Next
    INDEX
    Explanations

    references to waiting and lines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Altri
    -0.44
     uží
    -0.37
     koszt
    -0.36
    ActivityResult
    -0.34
     verbra
    -0.34
    arashtra
    -0.33
     siebie
    -0.30
     zuży
    -0.30
    cemment
    -0.30
    zież
    -0.29
    POSITIVE LOGITS
     queue
    1.06
     queues
    1.05
     queuing
    0.95
     Queue
    0.94
    Queue
    0.81
    queue
    0.79
     очередь
    0.79
    Queues
    0.76
     dequeue
    0.75
     deque
    0.75
    Activations Density 0.130%

    No Known Activations