© 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. 25-GEMMASCOPE-RES-16K
    11. 3089
    Prev
    Next
    INDEX
    Explanations

    elements related to code syntax and structure, particularly focusing on symbols and formatting used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     V
    -0.53
     L
    -0.51
     F
    -0.51
     B
    -0.51
     W
    -0.50
     J
    -0.49
     D
    -0.48
     P
    -0.48
     C
    -0.48
     Sm
    -0.48
    POSITIVE LOGITS
    hasOwnProperty
    0.80
     Adopted
    0.71
    TagMode
    0.70
     Offisielt
    0.68
    Adopted
    0.67
     незавершена
    0.66
    stateProvider
    0.65
    closePath
    0.64
     ejus
    0.64
     totalSupply
    0.63
    Activations Density 0.187%

    No Known Activations