© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 10038
    Prev
    Next
    INDEX
    Explanations

    programmatic structures and syntax elements in code-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -1.21
    complexContent
    -1.19
     EconPapers
    -1.17
    Personendaten
    -1.17
     kaarangay
    -1.13
     للاسماء
    -1.13
     propOrder
    -1.11
    Vidite
    -1.10
    InjectAttribute
    -1.07
     tartalomajánló
    -1.06
    POSITIVE LOGITS
    ,
    0.52
     to
    0.49
     
    0.49
     for
    0.49
     in
    0.47
     he
    0.45
    .
    0.44
    '
    0.41
     T
    0.39
    -
    0.39
    Activations Density 0.614%

    No Known Activations