© 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. 17-GEMMASCOPE-RES-16K
    11. 6131
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to contracts and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.73
    RegressionTest
    -0.72
     betweenstory
    -0.71
     appointing
    -0.65
    UnitTesting
    -0.64
    didSet
    -0.61
    ificity
    -0.60
     appoint
    -0.56
    ficie
    -0.56
     celu
    -0.55
    POSITIVE LOGITS
     work
    0.69
     working
    0.67
     job
    0.67
     helping
    0.60
     bekerja
    0.58
     работе
    0.56
     trabajar
    0.56
     travaille
    0.55
     professional
    0.55
     report
    0.54
    Activations Density 0.364%

    No Known Activations