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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8652
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Oxford."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.47
     gefü
    -0.44
     Mifflin
    -0.43
    SpringRunner
    -0.40
     geschlagen
    -0.39
    adpleegd
    -0.39
    MessageTagHelper
    -0.38
    Prairie
    -0.38
     Cardigan
    -0.38
     Luzon
    -0.37
    POSITIVE LOGITS
     Barcelona
    1.08
     Milan
    1.03
     Oxford
    0.98
     Swiss
    0.97
    Barcelona
    0.94
     Liverpool
    0.94
    Milan
    0.91
     Switzerland
    0.91
    Oxford
    0.88
     Geneva
    0.88
    Activations Density 0.136%

    No Known Activations