© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10504
    Prev
    Next
    INDEX
    Explanations

    references to legal fees and expenses in court documents

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

    Hourly rates or compensation

    np_acts-logits-general · gemini-2.0-flash

    hourly rates and fees

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.69
    VersionUID
    -0.66
    TabIndex
    -0.66
     resourceCulture
    -0.65
    ंदीखरीदारी
    -0.64
    SourceChecksum
    -0.60
    Viitteet
    -0.60
     tartalomajánló
    -0.58
    principalTable
    -0.57
     serien
    -0.57
    POSITIVE LOGITS
     hourly
    1.62
     rates
    1.37
     Hourly
    1.30
     rate
    1.28
    Hourly
    1.26
    hourly
    1.24
     hours
    1.21
     Rates
    1.17
     Rate
    1.16
     HOUR
    1.13
    Activations Density 0.217%

    No Known Activations