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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 12157
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary studies and nutrients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ElementRef
    -0.42
    adaptiveStyles
    -0.42
    untungan
    -0.36
    思わず
    -0.35
    Invoke
    -0.35
    ensch
    -0.35
    alo
    -0.35
    wanych
    -0.34
     nerve
    -0.34
     cack
    -0.34
    POSITIVE LOGITS
     nutrition
    0.97
     diet
    0.95
     diets
    0.90
     foods
    0.89
     dietary
    0.86
    foods
    0.85
     food
    0.85
     nutritional
    0.85
     alimentaires
    0.84
     Nutrition
    0.83
    Activations Density 0.665%

    No Known Activations