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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 8765
    Prev
    Next
    INDEX
    Explanations

    legal terms and references in court documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Pennsylvania legal context

    np_acts-logits-general · gemini-2.0-flash

    Pennsylvania legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.68
    WebVitals
    -0.59
     Malmö
    -0.57
    principalTable
    -0.57
     Lund
    -0.56
     Albuquerque
    -0.55
    XmlAccessType
    -0.55
    省市镇
    -0.54
     JsonConvert
    -0.53
     Rubio
    -0.52
    POSITIVE LOGITS
     Pennsylvania
    1.70
    Pennsylvania
    1.55
     Philadelphia
    1.41
     Penn
    1.35
     PENNSYLVANIA
    1.34
     PA
    1.30
     Philly
    1.28
     Penns
    1.27
     Harrisburg
    1.25
    Philadelphia
    1.25
    Activations Density 0.397%

    No Known Activations