© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14357
    Prev
    Next
    INDEX
    Explanations

    specific medical and technical terms related to various conditions and systems

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

    before "liver"

    np_acts-logits-general · gemini-2.0-flash

    medical, technical, and sports terms

    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
    Espèce
    -0.39
    exitRule
    -0.35
     gustaría
    -0.29
    исленность
    -0.29
     escapar
    -0.29
     Auf
    -0.28
     calcetines
    -0.28
     actuaciones
    -0.27
     ciudadana
    -0.27
     humanas
    -0.27
    POSITIVE LOGITS
     فريبيس
    0.72
    şört
    0.70
     ſta
    0.65
     houſe
    0.64
     ſche
    0.64
     Anſ
    0.62
     nakalista
    0.62
    Билгалдахарш
    0.61
    diode
    0.60
     Houſe
    0.60
    Activations Density 0.892%

    No Known Activations