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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 12080
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to fasting and blood analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.54
    writeField
    -0.53
     defaultstate
    -0.49
    onOptions
    -0.48
    MathML
    -0.46
    tagHelperRunner
    -0.45
     vVar
    -0.44
    writeFieldEnd
    -0.44
     Chwiliwch
    -0.43
     تقد
    -0.42
    POSITIVE LOGITS
     fasting
    1.50
    Fast
    1.33
     fast
    1.33
     Fasting
    1.30
    fast
    1.26
     Fast
    1.23
     FAST
    1.09
    FAST
    1.03
     faſt
    0.95
     fas
    0.93
    Activations Density 0.170%

    No Known Activations