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. 114530
    Prev
    Next
    INDEX
    Explanations

    expressions related to legal rights and self-representation in court

    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
     slä
    -0.42
     raí
    -0.35
    IContainer
    -0.35
    ฟ้า
    -0.35
     kerst
    -0.34
     cytoplasm
    -0.34
     newBuilder
    -0.34
    grond
    -0.33
     команди
    -0.33
     sfeer
    -0.32
    POSITIVE LOGITS
    resave
    0.52
    Autoritní
    0.52
     utafitiHapana
    0.51
    PageRoute
    0.50
     cherchés
    0.50
     ModelExpression
    0.49
    RTCK
    0.48
     שוליים
    0.48
     nakalista
    0.47
     GoogleFonts
    0.47
    Activations Density 0.089%

    No Known Activations