© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13416
    Prev
    Next
    INDEX
    Explanations

    relationships between parameters in data and their effects on specific outcomes

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

    after specific nouns (day, areas, effect, definition...)

    np_acts-logits-general · gemini-2.0-flash

    business operations

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    HasAnnotation
    -0.46
     menemp
    -0.35
    Бахар
    -0.34
    addCell
    -0.34
    rit
    -0.33
    TokenNameLBRACE
    -0.33
     memungkinkan
    -0.33
    住
    -0.33
     negó
    -0.32
     bł
    -0.32
    POSITIVE LOGITS
    wiſe
    0.73
     nor
    0.73
    httphttps
    0.72
    ſelf
    0.70
     itſelf
    0.65
    nor
    0.62
     anymore
    0.62
     transfieras
    0.59
     sondern
    0.57
     NOR
    0.57
    Activations Density 1.266%

    No Known Activations