© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14844
    Prev
    Next
    INDEX
    Explanations

    terms that relate to food, particularly emphasizing culinary experiences and gastronomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    food or dining experiences

    np_acts-logits-general · gemini-2.0-flash

    authentic local food specialties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.78
    tvguidetime
    -0.64
    طيع
    -0.60
     protoimpl
    -0.58
     Vernunft
    -0.58
    PoolSize
    -0.55
     باخ
    -0.51
    SharedDtor
    -0.48
    namentales
    -0.48
    раздо
    -0.47
    POSITIVE LOGITS
     traditional
    0.94
     locally
    0.93
     specialties
    0.90
     authentic
    0.89
     delicious
    0.83
     delicacies
    0.83
    traditional
    0.82
     speciality
    0.81
     specialty
    0.81
     homemade
    0.80
    Activations Density 0.192%

    No Known Activations