© 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. 41-GEMMASCOPE-RES-16K
    11. 10803
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating uncertainty or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    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
    -1.84
     myself
    -1.48
     mijn
    -1.36
    I
    -1.36
     meinem
    -1.31
     minha
    -1.27
     meiner
    -1.27
     meines
    -1.27
     meine
    -1.25
     meu
    -1.20
    POSITIVE LOGITS
     I
    0.83
     للاسماء
    0.65
     &___
    0.56
    enderror
    0.55
     дописавши
    0.52
    ICOLON
    0.50
    GEBURTSDATUM
    0.48
    ▍
    0.47
     ISNI
    0.47
    TemporalType
    0.47
    Activations Density 0.448%

    No Known Activations