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

    Neuronpedia

    Jacobian LensNEW
    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. 10151
    Prev
    Next
    INDEX
    Explanations

    numerical data related to specific events or metrics

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

    Numbers followed by date-related words/numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by 2, 7, 6, 8, 0, 5

    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
     pinulongan
    -0.73
    Aujourd
    -0.67
     Today
    -0.65
     today
    -0.65
    today
    -0.59
     autorytatywna
    -0.59
     Heute
    -0.57
     hoy
    -0.57
     Current
    -0.56
     Signalez
    -0.55
    POSITIVE LOGITS
     förra
    0.59
     last
    0.57
    Obrázky
    0.51
    ImageContext
    0.50
    SharedDtor
    0.49
    těte
    0.49
    writeFieldEnd
    0.49
    
    0.49
     Wicidata
    0.48
     تضيفلها
    0.48
    Activations Density 0.169%

    No Known Activations