© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104408
    Prev
    Next
    INDEX
    Explanations

    references to parties involved in legal proceedings

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

    Terms designating one entity in a binary relationship, often in legal, technical, or scientific contexts where two parties or endpoints interact or oppose each other.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ValueStyle
    -0.72
    UrlResolution
    -0.71
    LEncoder
    -0.71
    msgTypes
    -0.67
     estekak
    -0.67
    脚注の使い方
    -0.66
    RegressionTest
    -0.65
    Personensuche
    -0.64
     فريبيس
    -0.63
     الرياضيه
    -0.63
    POSITIVE LOGITS
    (!__
    0.34
    BASEPATH
    0.34
    lijck
    0.28
    genheit
    0.26
     порядке
    0.26
    extrême
    0.26
     Justicia
    0.25
     Lippen
    0.25
    bleiben
    0.25
     zob
    0.25
    Activations Density 0.064%

    No Known Activations