Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12663
    Prev
    Next
    INDEX
    Explanations

    references related to food markets or culinary experiences

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

    Food stalls or markets

    np_acts-logits-general · gemini-2.0-flash

    food court, markets, selling

    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
    Filmographie
    -0.59
    RegressionTest
    -0.55
    rlpool
    -0.54
    bní
    -0.53
    tvguidetime
    -0.52
    égio
    -0.51
    sendTo
    -0.50
    obbies
    -0.50
    inghouse
    -0.50
    Véxase
    -0.49
    POSITIVE LOGITS
     stalls
    1.39
     vendors
    1.35
     stall
    1.35
     vendor
    1.30
     booth
    1.18
     Vendors
    1.17
     booths
    1.16
    Vendors
    1.08
    vendors
    1.08
     stands
    1.06
    Activations Density 0.127%

    No Known Activations