© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 105479
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to public performance and accountability

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Connective tokens (prepositions, conjunctions, possessives) and action verbs that establish relationships between entities in text or complete grammatical constructions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
     fracas
    -0.39
     sector
    -0.38
     kép
    -0.36
     Critics
    -0.36
    StandardCharsets
    -0.35
     iNdEx
    -0.35
    Склад
    -0.35
    ข
    -0.35
     везе
    -0.34
     sceptical
    -0.34
    POSITIVE LOGITS
    RegressionTest
    0.53
     للمعارف
    0.53
     "..\..\..\
    0.53
     "..\..\
    0.52
    省市镇
    0.50
     Anſ
    0.49
     متعلقه
    0.49
    Autoritní
    0.48
     ")");
    0.47
     &___
    0.47
    Activations Density 0.303%

    No Known Activations