© 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. 33-GEMMASCOPE-RES-16K
    11. 11350
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and operations related to derivatives and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.51
    IBOutlet
    -0.49
    ="@+
    -0.44
    XmlEnum
    -0.43
     dėl
    -0.41
    felizmente
    -0.41
     usually
    -0.41
     JAXBElement
    -0.41
     sprang
    -0.40
     springing
    -0.40
    POSITIVE LOGITS
    Hint
    0.92
     Hint
    0.88
    hint
    0.77
    HINT
    0.75
     hint
    0.75
    Hints
    0.73
     Hints
    0.72
     hints
    0.66
    hints
    0.63
     Jus
    0.60
    Activations Density 0.883%

    No Known Activations