© 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. 11-GEMMASCOPE-RES-16K
    11. 10207
    Prev
    Next
    INDEX
    Explanations

    references to containers, specifically bowls and cups, typically in the context of cooking or serving food and drinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hera
    -0.60
     Juno
    -0.59
    alma
    -0.55
     Maurice
    -0.55
     Algo
    -0.54
    daun
    -0.54
    neri
    -0.54
     Eilish
    -0.53
    Juni
    -0.52
    juni
    -0.52
    POSITIVE LOGITS
     cup
    0.98
    Cup
    0.97
     bowl
    0.91
    Bowl
    0.91
     Cup
    0.89
     Bowl
    0.88
     taza
    0.84
     cups
    0.84
    cup
    0.83
     CUP
    0.76
    Activations Density 0.234%

    No Known Activations