© 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. 20-GEMMASCOPE-RES-16K
    11. 4438
    Prev
    Next
    INDEX
    Explanations

    programming syntax and function definitions

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

    Code snippets with print statements

    np_acts-logits-general · gemini-2.0-flash

    printing and returning values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    mybatisplus
    -0.56
    ennom
    -0.52
     Zü
    -0.48
    Carreira
    -0.46
     Beobachtungen
    -0.45
    ディション
    -0.43
    γωγ
    -0.43
    inerja
    -0.42
     consideration
    -0.42
    FunctionFlags
    -0.42
    POSITIVE LOGITS
    print
    1.90
     print
    1.88
     Print
    1.58
     PRINT
    1.53
    Print
    1.53
     prints
    1.52
     println
    1.48
    println
    1.46
    Console
    1.45
     printf
    1.43
    Activations Density 0.320%

    No Known Activations