© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1309
    Prev
    Next
    INDEX
    Explanations

    terms related to the human digestive system and gastrointestinal issues

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

    digestion and the intestines

    np_acts-logits-general · gemini-2.0-flash

    digestive system and intestinal tract

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    awtextra
    -0.59
    Datuak
    -0.57
     otomatig
    -0.55
     AttributeSet
    -0.55
    jsonwebtoken
    -0.54
     المعيارى
    -0.53
    الحياه
    -0.51
     kasarigan
    -0.51
    CardBody
    -0.51
     $_(
    -0.51
    POSITIVE LOGITS
     digestive
    0.71
     intestine
    0.67
     stomach
    0.66
     Digestive
    0.65
    Gastro
    0.64
     gastro
    0.62
     Stomach
    0.61
     intestinal
    0.60
     Gastro
    0.60
     Gastroenter
    0.60
    Activations Density 0.379%

    No Known Activations