© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13689
    Prev
    Next
    INDEX
    Explanations

    declarations of private static variables in programming code

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

    Variables, often "private" ones

    np_acts-logits-general · gemini-2.0-flash

    programming variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     autorytatywna
    -0.39
    maketitle
    -0.38
     évé
    -0.35
     popoli
    -0.34
    EditorGUILayout
    -0.34
    Földrajzportál
    -0.34
    onSearch
    -0.34
     volverá
    -0.34
     recomienda
    -0.34
    onBackPressed
    -0.33
    POSITIVE LOGITS
     protoimpl
    0.61
    synthesize
    0.59
    Datuak
    0.57
     referenties
    0.56
     propOrder
    0.54
     समीक्षाओं
    0.53
     initComponents
    0.52
     препратки
    0.51
    tagHelperRunner
    0.50
     kaarangay
    0.48
    Activations Density 0.061%

    No Known Activations