© 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. 7206
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and documentation elements related to custom elements in programming

    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
     للمعارف
    -0.53
    HideFlags
    -0.41
    żesz
    -0.39
    MLLoader
    -0.39
    ?.
    -0.39
     Paglinawan
    -0.38
     ?:
    -0.37
    atigable
    -0.37
    ?).
    -0.36
    grés
    -0.36
    POSITIVE LOGITS
    pub
    0.96
     fn
    0.91
    fn
    0.89
     pub
    0.89
    #[
    0.70
    impl
    0.70
    Pub
    0.68
     mod
    0.66
     Pub
    0.65
    mod
    0.64
    Activations Density 0.303%

    No Known Activations