© 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. 42653
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control flow structures in programming code

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

    if followed by parenthesis

    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
     kautta
    -0.39
     sarili
    -0.38
     ajouté
    -0.35
     respald
    -0.35
     erweiterten
    -0.34
     leicht
    -0.32
     lisäksi
    -0.32
     acá
    -0.32
     kanssa
    -0.32
    CFLAGS
    -0.31
    POSITIVE LOGITS
    Personendaten
    0.86
     queſta
    0.83
    \{\\
    0.78
    matchCondition
    0.77
    
    0.76
    <unused76>
    0.75
    ſſung
    0.75
    <unused1>
    0.75
    <unused8>
    0.74
    <unused23>
    0.74
    Activations Density 0.012%

    No Known Activations