© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 16080
    Prev
    Next
    INDEX
    Explanations

    instances of the word "matching" and related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     étoient
    -0.70
     purpoſe
    -0.70
     pleaſure
    -0.69
     avoient
    -0.67
     Shakspeare
    -0.65
    IntoConstraints
    -0.63
     photolibrary
    -0.62
     $_"
    -0.62
    ſelves
    -0.62
     myſelf
    -0.60
    POSITIVE LOGITS
     matching
    1.18
     MATCH
    1.15
     match
    1.13
     matched
    1.08
    matching
    1.06
     Match
    1.05
     Matching
    1.05
    matched
    1.05
    MATCH
    1.01
    Matching
    1.01
    Activations Density 0.125%

    No Known Activations