© 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. 42468
    Prev
    Next
    INDEX
    Explanations

    conversations involving requests and introductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introductions and explanations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     zasi
    -0.55
     lojas
    -0.54
     rodillas
    -0.52
     penilaian
    -0.51
     recuperación
    -0.50
    aurait
    -0.48
     actualidad
    -0.48
    ibição
    -0.48
     énergé
    -0.47
     sonrisa
    -0.46
    POSITIVE LOGITS
     الحره
    0.66
    Personendaten
    0.63
     محفوظة
    0.53
    findpost
    0.53
     كومونز
    0.51
    SequentialGroup
    0.50
    zzleHttp
    0.50
    ChildIndex
    0.49
    AndEndTag
    0.48
    StoreMessageInfo
    0.47
    Activations Density 0.008%

    No Known Activations