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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14400
    Prev
    Next
    INDEX
    Explanations

    phrases related to various forms of economic activity

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

    before food items

    np_acts-logits-general · gemini-2.0-flash

    produced or processed items

    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
     kiin
    -0.66
     vastaan
    -0.62
     gezet
    -0.58
     pysty
    -0.57
     ilmo
    -0.56
     kılıf
    -0.56
     dalamnya
    -0.55
     braços
    -0.53
     yrity
    -0.53
     amortecedor
    -0.53
    POSITIVE LOGITS
     milk
    1.25
     chocolate
    1.25
     sugar
    1.19
     coffee
    1.18
     eggs
    1.15
     cheese
    1.15
     potatoes
    1.14
     vodka
    1.14
     butter
    1.13
     tomatoes
    1.13
    Activations Density 1.170%

    No Known Activations