© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3570
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to coding functions and print statements

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

    Code that prints to console or standard output

    np_acts-logits-general · gemini-2.0-flash

    console output and printing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Становништво
    -0.51
    VIAF
    -0.48
    __]
    -0.47
    mobileqq
    -0.46
    FunctionFlags
    -0.46
    المكان
    -0.46
     VIAF
    -0.45
     учета
    -0.45
    ディション
    -0.43
    wifery
    -0.43
    POSITIVE LOGITS
    print
    1.88
     print
    1.86
     Print
    1.55
     prints
    1.53
    Print
    1.53
     PRINT
    1.47
    PRINT
    1.43
     printed
    1.38
    Console
    1.38
    println
    1.36
    Activations Density 0.508%

    No Known Activations