© 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. 104832
    Prev
    Next
    INDEX
    Explanations

    qualifying statements and expressions of nuance in opinions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
     surla
    -0.48
     Pakai
    -0.45
     jspb
    -0.44
     costumbre
    -0.43
     tóxic
    -0.43
     abandonné
    -0.42
    經過
    -0.41
    opsida
    -0.40
     ComVisible
    -0.40
     ilman
    -0.39
    POSITIVE LOGITS
    lında
    0.54
    一見
    0.51
    ContentAsync
    0.49
    ContentValues
    0.47
    LikeLike
    0.46
    发表于
    0.46
    complexContent
    0.46
    VersionUID
    0.43
    InSection
    0.43
    riebe
    0.42
    Activations Density 0.020%

    No Known Activations