© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13445
    Prev
    Next
    INDEX
    Explanations

    elements in code that denote the structure and syntax of programming language constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Square brackets

    np_acts-logits-general · gemini-2.0-flash

    programming data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.48
    vestre
    -0.45
    ':
    -0.45
    Coca
    -0.43
    -
    -0.43
    brücke
    -0.43
    Recognizer
    -0.43
     Coca
    -0.43
    awtextra
    -0.42
    '}>
    -0.42
    POSITIVE LOGITS
    []
    0.77
     []
    0.65
    تقاوى
    0.63
     [][]
    0.57
     springfox
    0.56
     <>",
    0.56
    [][]
    0.56
    [];
    0.55
     [];
    0.53
    |[]
    0.52
    Activations Density 0.131%

    No Known Activations