© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 2888
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to discrimination cases in court documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.78
    LookAnd
    -0.75
     Biôgrafia
    -0.68
     Theſe
    -0.67
     Monfieur
    -0.65
    RenderAtEndOf
    -0.63
     européennes
    -0.63
    躇
    -0.63
     Italijanski
    -0.62
     ModelAndView
    -0.62
    POSITIVE LOGITS
     mortgage
    0.74
    gaged
    0.70
     lien
    0.66
    Mortgage
    0.66
     typelib
    0.65
     liens
    0.65
     Mortgage
    0.61
    mortgage
    0.60
     mortgages
    0.60
    migrationBuilder
    0.57
    Activations Density 1.510%

    No Known Activations