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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 105498
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to diversity and representation in narratives

    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
     CURIAM
    -0.71
    ="@+
    -0.52
    +:+
    -0.45
    cfm
    -0.43
    gink
    -0.42
    TInt
    -0.42
     اكتوبر
    -0.41
    ngOn
    -0.41
     setSelected
    -0.41
     clearfix
    -0.40
    POSITIVE LOGITS
     disambiguazione
    0.54
     tartalomajánló
    0.52
    Personensuche
    0.46
    setDo
    0.46
    ativement
    0.45
     Вікіпе
    0.44
    zyden
    0.44
     financiación
    0.42
     Zappa
    0.42
    もちゃ
    0.42
    Activations Density 0.068%

    No Known Activations