© 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. 15385
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control flow structures in code

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

    Code immediately following an "if" statement

    np_acts-logits-general · gemini-2.0-flash

    if statements

    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
    BagLayout
    -0.64
    
    -0.59
    ConstraintMaker
    -0.57
    tagHelperRunner
    -0.57
    ;#
    -0.56
    *{-
    -0.55
    تفصیلات
    -0.52
     الكه
    -0.51
     Pute
    -0.51
    ždy
    -0.51
    POSITIVE LOGITS
     propOrder
    0.66
     autorytatywna
    0.60
     Waray
    0.56
     typeof
    0.55
    NgModule
    0.54
    ItemBackground
    0.51
     ['
    0.50
    (['
    0.50
    crite
    0.50
    typeof
    0.49
    Activations Density 0.024%

    No Known Activations