© 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. 9-GEMMASCOPE-RES-131K
    11. 13520
    Prev
    Next
    INDEX
    Explanations

    instances of the string "Re"

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

    reply prefix or "RE" start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    CppMethod
    -0.81
     estekak
    -0.80
    tagHelperRunner
    -0.77
     nahilalakip
    -0.63
     незавершена
    -0.63
     kasarigan
    -0.60
     beginnetje
    -0.59
    enderror
    -0.58
    /**
    -0.58
    msgTypes
    -0.57
    POSITIVE LOGITS
    Re
    0.80
     Re
    0.55
     RE
    0.53
    Regarding
    0.50
     re
    0.48
     betreff
    0.47
    RE
    0.46
    re
    0.46
     Regarding
    0.45
     bezüglich
    0.44
    Activations Density 0.022%

    No Known Activations