© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 121035
    Prev
    Next
    INDEX
    Explanations

    references to web development resources and libraries

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

    start of user turn

    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
    docx
    -0.48
     omge
    -0.42
     gezet
    -0.41
     gehouden
    -0.41
    zelfde
    -0.41
     inhoud
    -0.40
     praktijk
    -0.39
     afspraak
    -0.39
     piena
    -0.39
     mukaan
    -0.39
    POSITIVE LOGITS
    hoeddwyd
    0.68
    httphttps
    0.59
    jsxFileName
    0.57
    GIVEREF
    0.56
     cherchés
    0.55
    GTCX
    0.54
    WithMany
    0.51
    Personensuche
    0.48
     مشين
    0.47
     كومونز
    0.47
    Activations Density 0.005%

    No Known Activations