© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11218
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology, court jurisdictions, and professional qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éramos
    -0.29
     botines
    -0.28
     Hü
    -0.28
     Arabs
    -0.28
     arabe
    -0.27
    SourceChecksum
    -0.27
    成田
    -0.27
    ARAB
    -0.27
    kk
    -0.26
     crossorigin
    -0.26
    POSITIVE LOGITS
     Illinois
    1.94
     Pennsylvania
    1.89
     Ohio
    1.84
     Wisconsin
    1.84
     California
    1.84
     Texas
    1.80
     Florida
    1.80
     Massachusetts
    1.78
     Alabama
    1.77
     Michigan
    1.77
    Activations Density 1.253%

    No Known Activations