© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 5412
    Prev
    Next
    INDEX
    Explanations

    usage of specific conjunctions and possessive pronouns

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

    personal names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    enterOuterAlt
    -0.52
     kasarigan
    -0.46
    addCriterion
    -0.42
     Unterscheidung
    -0.41
    存于互联网档案馆
    -0.41
    :+:
    -0.40
    aturing
    -0.38
    <?
    -0.38
    webElement
    -0.37
    featureID
    -0.37
    POSITIVE LOGITS
     named
    0.56
     Named
    0.54
     name
    0.51
    named
    0.50
     nama
    0.48
    Named
    0.48
     नाम
    0.48
    Personendaten
    0.45
     '\\;'
    0.45
     surname
    0.44
    Activations Density 0.320%

    No Known Activations