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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103141
    Prev
    Next
    INDEX
    Explanations

    terms related to digestive health and gastrointestinal functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    unteer
    -0.56
    emptory
    -0.53
    lichter
    -0.52
     otomatig
    -0.51
    setClass
    -0.51
     հղումներ
    -0.51
    AutoField
    -0.50
    ortage
    -0.49
    IDATE
    -0.49
     userList
    -0.49
    POSITIVE LOGITS
     digestive
    0.61
     Digestive
    0.51
     digestion
    0.46
     indigestion
    0.45
    extAlignment
    0.44
     EconPapers
    0.42
    消化
    0.42
     Digestion
    0.40
     digesti
    0.39
    Gastro
    0.38
    Activations Density 0.011%

    No Known Activations