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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9475
    Prev
    Next
    INDEX
    Explanations

    references to competitive gaming or strategy mechanics

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

    Game-related terms (offensive, defensive, spells)

    np_acts-logits-general · gemini-2.0-flash

    offensive spells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.77
    migrationBuilder
    -0.74
    RTDA
    -0.67
     OBB
    -0.65
    InitVars
    -0.64
    GOTREF
    -0.63
    complexType
    -0.60
     actionPerformed
    -0.59
    tagHelperRunner
    -0.59
    انيف
    -0.58
    POSITIVE LOGITS
     champions
    0.67
     lane
    0.66
     champion
    0.65
     ADC
    0.64
     jungle
    0.61
     jung
    0.58
     lanes
    0.55
     Lane
    0.54
    champion
    0.54
     adc
    0.54
    Activations Density 0.071%

    No Known Activations