© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 114746
    Prev
    Next
    INDEX
    Explanations

    conjunctions that introduce contrasting clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    PackageName
    -0.42
     corne
    -0.41
     réservoir
    -0.41
     Ankara
    -0.37
     carre
    -0.36
     Keluarga
    -0.36
    Deskripsi
    -0.36
     moto
    -0.35
     moteur
    -0.35
     coj
    -0.34
    POSITIVE LOGITS
    though
    0.92
     though
    0.87
    however
    0.73
     THOUGH
    0.72
    прочем
    0.71
     quizá
    0.71
     choć
    0.71
    ांकि
    0.68
    尽管
    0.68
     meskipun
    0.68
    Activations Density 0.017%

    No Known Activations