© 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. 20-GEMMASCOPE-RES-16K
    6. 14735
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases in Pennsylvania

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.65
    AndEndTag
    -0.61
     nahilalakip
    -0.57
    ChildScrollView
    -0.57
    CompilerServices
    -0.57
    interopRequire
    -0.54
    يكب
    -0.54
     itſelf
    -0.54
     ſich
    -0.53
    toJSONString
    -0.53
    POSITIVE LOGITS
     Pennsylvania
    0.80
    Pennsylvania
    0.79
     Pittsburgh
    0.76
     Philadelphia
    0.69
    Pittsburgh
    0.68
     Allegheny
    0.68
    Philadelphia
    0.66
     Philly
    0.64
     Philadel
    0.60
    ADELPHIA
    0.60
    Activations Density 0.440%

    No Known Activations