© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11635
    Prev
    Next
    INDEX
    Explanations

    words and characters from various languages, particularly those related to specific cultural contexts

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

    non-Latin script characters and text in Indian languages (Devanagari, Kannada, Gujarati, etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zuſammen
    -0.80
     zwiſchen
    -0.79
     الحره
    -0.79
     beſte
    -0.76
    ſicht
    -0.76
     unſer
    -0.75
     témoig
    -0.75
     ddelwed
    -0.74
     geſch
    -0.74
     imagui
    -0.73
    POSITIVE LOGITS
    曖昧さ回避
    0.35
     pály
    0.30
     politiet
    0.30
     rzecz
    0.30
     spørs
    0.29
    आ
    0.29
     čierna
    0.29
     upto
    0.28
     físico
    0.28
     henvisninger
    0.28
    Activations Density 0.003%

    No Known Activations