© 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. 10-GEMMASCOPE-RES-16K
    6. 12221
    Prev
    Next
    INDEX
    Explanations

    elements related to various governance, political, and cultural topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.63
     intere
    -0.54
     Pfund
    -0.54
    TotalCount
    -0.54
    ICIA
    -0.53
    Amigo
    -0.50
     Bergmann
    -0.50
     Schnell
    -0.49
     Peterson
    -0.48
     geni
    -0.48
    POSITIVE LOGITS
    deutig
    0.61
     alugar
    0.61
    Хьажоргаш
    0.59
    GEBURTSDATUM
    0.56
     fiscale
    0.56
     shuts
    0.55
    thschild
    0.54
    смотра
    0.53
    ähteet
    0.53
     scolas
    0.52
    Activations Density 8.036%

    No Known Activations