© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 40-GEMMASCOPE-RES-16K
    11. 2965
    Prev
    Next
    INDEX
    Explanations

    expressions related to conversation or dialogue about personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.63
    astéroïdes
    -0.52
     Füßen
    -0.52
    orologio
    -0.49
    amica
    -0.48
     Überg
    -0.47
    dowa
    -0.47
     urodz
    -0.47
     брать
    -0.46
     kasarigan
    -0.46
    POSITIVE LOGITS
     témoig
    0.49
     vectorielle
    0.48
     ainfi
    0.45
     mauva
    0.44
     feroit
    0.43
     vectorielles
    0.42
     pouvoit
    0.41
     financières
    0.41
     quelcon
    0.39
     démocr
    0.38
    Activations Density 0.201%

    No Known Activations