© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15408
    Prev
    Next
    INDEX
    Explanations

    references to control flow structures in programming

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

    Code keywords: "loop", "case", "else", "while"

    np_acts-logits-general · gemini-2.0-flash

    loops and branching

    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
     TextInputType
    -0.67
     שוליים
    -0.63
    ђа
    -0.60
    OGND
    -0.58
     виправивши
    -0.57
     }}"></
    -0.56
    eradish
    -0.56
     teg
    -0.54
    uxxxx
    -0.52
    esModule
    -0.52
    POSITIVE LOGITS
     loop
    1.30
    loop
    1.17
     Loop
    1.12
     loops
    1.11
    Loop
    1.05
     Loops
    1.02
     looping
    0.99
    loops
    0.98
     while
    0.95
    循环
    0.94
    Activations Density 0.780%

    No Known Activations