© 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. 14359
    Prev
    Next
    INDEX
    Explanations

    words and characters from various languages, especially those related to geographical names and currencies

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

    Non-English words or characters

    np_acts-logits-general · gemini-2.0-flash

    foreign script and symbols

    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
     sentin
    -0.59
     vooz
    -0.57
    ulemon
    -0.55
    RegressionTest
    -0.55
     imagui
    -0.55
    TintMode
    -0.55
     témoig
    -0.54
    ᅠ
    -0.53
     FacebookSign
    -0.52
     daysTop
    -0.52
    POSITIVE LOGITS
    œurs
    0.35
     própria
    0.35
    SourceChecksum
    0.34
     JFrame
    0.34
    Sede
    0.34
     ويكيپيديا
    0.33
    rsiniz
    0.32
    Myself
    0.32
     próprios
    0.32
    richTextPanel
    0.32
    Activations Density 0.139%

    No Known Activations