© 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. 20-GEMMASCOPE-RES-16K
    11. 13251
    Prev
    Next
    INDEX
    Explanations

    key terms related to food safety and contamination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parameteri
    -0.39
    expliquer
    -0.39
     durer
    -0.38
     résister
    -0.38
     graça
    -0.38
     يتيمه
    -0.35
     pontu
    -0.35
     الحره
    -0.35
    ťa
    -0.34
     Dempsey
    -0.34
    POSITIVE LOGITS
     contamination
    0.62
     Food
    0.61
     food
    0.60
     Contamination
    0.60
    ፩
    0.59
    Food
    0.59
    Personensuche
    0.59
    StructEnd
    0.58
     nonUne
    0.58
     contaminate
    0.58
    Activations Density 0.095%

    No Known Activations