© 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. 11961
    Prev
    Next
    INDEX
    Explanations

    segments related to programming syntax or code structures

    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
    parsedMessage
    -0.80
     tartalomajánló
    -0.79
    RegistryLite
    -0.69
     Económica
    -0.68
     виправивши
    -0.68
     EconPapers
    -0.68
     Wikiseite
    -0.66
    AutoScale
    -0.65
     kasarigan
    -0.64
     كومونز
    -0.64
    POSITIVE LOGITS
     fu
    0.37
    ferrous
    0.36
    сятся
    0.36
     mas
    0.36
     ins
    0.36
     As
    0.35
     Fu
    0.34
     Bol
    0.34
     bol
    0.34
     Pav
    0.34
    Activations Density 2.418%

    No Known Activations