© 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. 38-GEMMASCOPE-RES-16K
    11. 8789
    Prev
    Next
    INDEX
    Explanations

    conversational phrases or expressions involving personal pronouns and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     def
    -0.57
     main
    -0.56
     sim
    -0.56
     base
    -0.56
     file
    -0.55
     ver
    -0.55
     gra
    -0.54
     franchise
    -0.54
     bes
    -0.54
     del
    -0.53
    POSITIVE LOGITS
     berdua
    0.46
     ślub
    0.40
     Económica
    0.39
     Erfindung
    0.39
    ających
    0.38
    AndEndTag
    0.38
     Absicht
    0.37
     wystarczy
    0.37
     chcą
    0.37
     triliun
    0.37
    Activations Density 0.091%

    No Known Activations