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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13723
    Prev
    Next
    INDEX
    Explanations

    references to legal qualifications and professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    •Law

    No Comments

    Negative Logits
    MemoryWarning
    -0.72
     OnInit
    -0.68
     محفوظة
    -0.67
     MonoBehaviour
    -0.64
    GraphicsUnit
    -0.61
    UrlResolution
    -0.58
     الحره
    -0.58
    AutoScaleMode
    -0.55
    WaitGroup
    -0.51
     lenker
    -0.50
    POSITIVE LOGITS
     lawyers
    2.06
     lawyer
    1.94
     attorneys
    1.92
     Lawyers
    1.90
     attorney
    1.82
    lawyer
    1.81
     Lawyer
    1.78
     Legal
    1.74
     legal
    1.72
    Lawyer
    1.71
    Activations Density 0.691%

    No Known Activations