© 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. 379
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to sorting and comparison functions

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

    Ordering or comparing elements

    np_acts-logits-general · gemini-2.0-flash

    comparison operators and ordering

    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
    AnchorStyles
    -0.65
    Controllo
    -0.63
    ="@+
    -0.59
    tagHelperRunner
    -0.58
     autorytatywna
    -0.58
     архивлан
    -0.57
    Westfalen
    -0.55
     ***!
    -0.55
    setVerticalGroup
    -0.55
    ModelAdmin
    -0.55
    POSITIVE LOGITS
     compare
    1.25
     Compare
    1.19
    Compare
    1.14
     comparing
    1.12
     compares
    1.10
    compare
    1.10
     comparison
    1.09
     comparisons
    1.04
     Comparing
    1.03
     Comparison
    0.97
    Activations Density 0.772%

    No Known Activations