© 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. 22566
    Prev
    Next
    INDEX
    Explanations

    sections of code or programming constructs

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

    multi-language code and technical terms

    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
    setVerticalGroup
    -0.82
    SharedCtor
    -0.73
    NameInMap
    -0.72
     nakalista
    -0.68
     esternos
    -0.68
     resourceCulture
    -0.65
    ########.
    -0.63
    SharedDtor
    -0.62
    :✨
    -0.62
    Personensuche
    -0.61
    POSITIVE LOGITS
    ValueGenerated
    0.37
     skolen
    0.36
     endgül
    0.34
    melidir
    0.30
     Geburt
    0.30
    mode
    0.30
     coordonnées
    0.30
     Nunn
    0.29
     Gerechtigkeit
    0.29
     prochaines
    0.29
    Activations Density 0.244%

    No Known Activations