© 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. 4990
    Prev
    Next
    INDEX
    Explanations

    references to unconventional or unusual culinary dishes and dining experiences

    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
    pride
    -0.37
    发表于
    -0.35
    ])));
    -0.34
     pride
    -0.34
    蚪
    -0.33
    Pride
    -0.32
     exécu
    -0.31
    ябрь
    -0.31
    chism
    -0.30
     allAfrica
    -0.30
    POSITIVE LOGITS
     unusual
    1.27
     unconventional
    1.20
     Unusual
    1.18
    Unusual
    1.16
    unusual
    1.15
     weird
    1.01
     atypical
    1.00
     bizarre
    0.95
     inusual
    0.94
     Weird
    0.94
    Activations Density 0.537%

    No Known Activations