© 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. 33-GEMMASCOPE-RES-16K
    11. 11380
    Prev
    Next
    INDEX
    Explanations

    descriptions of dietary patterns and their health implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sabun
    -0.46
     caucho
    -0.44
     ElementRef
    -0.44
    ractable
    -0.38
    橡胶
    -0.38
     governador
    -0.38
     rubber
    -0.38
    нутрен
    -0.38
     Rubber
    -0.38
    annels
    -0.37
    POSITIVE LOGITS
    HtmlAttribute
    0.63
    مصادر
    0.58
    findpost
    0.57
     foods
    0.57
     ब्रेकडाउन
    0.56
    Foods
    0.55
     carbs
    0.54
    摄
    0.54
    ItemBackground
    0.54
     calories
    0.51
    Activations Density 0.356%

    No Known Activations