© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80515
    Prev
    Next
    INDEX
    Explanations

    ingredients and measurements related to food and cooking

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

    water and liquids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.75
     незавершена
    -0.72
    IUrlHelper
    -0.68
    writeField
    -0.63
    AddTagHelper
    -0.62
    niająca
    -0.59
    RefNanny
    -0.58
    bootstrapcdn
    -0.58
    destroyAll
    -0.57
    haikusbot
    -0.57
    POSITIVE LOGITS
     water
    0.37
    水
    0.32
     trajets
    0.29
    JScrollPane
    0.28
     Water
    0.28
     till
    0.28
    vass
    0.28
    OrEqual
    0.27
    wsdl
    0.27
    够
    0.27
    Activations Density 0.023%

    No Known Activations