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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3957
    Prev
    Next
    INDEX
    Explanations

    references to specific types of foods and dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.57
     FSC
    -0.49
     mümkün
    -0.48
    FSC
    -0.46
     Omaha
    -0.46
    WebVitals
    -0.46
     kılıf
    -0.45
     propOrder
    -0.45
    webElementXpaths
    -0.43
     Elo
    -0.42
    POSITIVE LOGITS
     Turkish
    2.20
     Turkey
    2.09
    Turkish
    1.94
    Turkey
    1.93
     Istanbul
    1.75
     turkish
    1.74
     Turquía
    1.73
     turkey
    1.70
     Turks
    1.66
     Ankara
    1.65
    Activations Density 0.150%

    No Known Activations