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. 40824
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical connections and configurations in devices

    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
    protoimpl
    -0.96
     autorytatywna
    -0.75
     jspb
    -0.67
    setupUi
    -0.64
    Personendaten
    -0.60
     protoimpl
    -0.58
     initComponents
    -0.58
     jsPsych
    -0.57
    endpush
    -0.57
    mybatisplus
    -0.57
    POSITIVE LOGITS
     Vielzahl
    0.36
     pelayanan
    0.35
     protectora
    0.35
     energía
    0.35
     plegable
    0.34
     véhicule
    0.33
     religión
    0.33
     plástica
    0.33
     clínico
    0.33
     readily
    0.32
    Activations Density 0.842%

    No Known Activations