© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 2822
    Prev
    Next
    INDEX
    Explanations

    questions reflecting uncertainty or self-doubt about choices and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     my
    -1.79
     mijn
    -1.46
     minha
    -1.34
     mój
    -1.32
    我的
    -1.32
     moje
    -1.32
     meinem
    -1.31
     meu
    -1.31
     meus
    -1.29
     miei
    -1.28
    POSITIVE LOGITS
     I
    1.51
     we
    0.69
     informée
    0.52
    I
    0.51
     я
    0.49
     i
    0.47
     aš
    0.46
     للاسماء
    0.44
    Ⅰ
    0.42
    their
    0.41
    Activations Density 0.837%

    No Known Activations