© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5071
    Prev
    Next
    INDEX
    Explanations

    information about football clubs and players

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

    Caribbean locations and soccer

    np_acts-logits-general · gemini-2.0-flash

    Caribbean countries and nationalities

    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
     CreateTagHelper
    -0.75
    Билгалдахарш
    -0.72
    galus
    -0.67
    InvalidProtocol
    -0.65
    reportWebVitals
    -0.61
    SerializedSize
    -0.60
     CHtml
    -0.59
     NDEBUG
    -0.57
    almaz
    -0.57
    OrBuilder
    -0.57
    POSITIVE LOGITS
     Caribbean
    1.51
    Caribbean
    1.27
     Barbados
    1.26
     caribbean
    1.15
     Dominica
    1.10
     Jamaica
    1.09
     Jamaican
    1.09
     Antigua
    1.08
     Trinidad
    1.07
     Nevis
    1.05
    Activations Density 0.138%

    No Known Activations