© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9840
    Prev
    Next
    INDEX
    Explanations

    instances of the word "match" and its variations, indicating a focus on comparisons or agreements between items or concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Portale
    -0.63
     newUser
    -0.61
    errHandler
    -0.60
    ChildScrollView
    -0.59
    execSQL
    -0.52
     newName
    -0.48
    anthene
    -0.46
     esternos
    -0.45
    newUser
    -0.45
     Fonseca
    -0.44
    POSITIVE LOGITS
     Match
    1.12
     match
    1.11
    match
    1.05
    Match
    1.04
     MATCH
    1.02
    MATCH
    0.92
     Matches
    0.83
     matches
    0.82
     matched
    0.81
    Matcher
    0.76
    Activations Density 0.169%

    No Known Activations