© 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. 4891
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly in a statistical or financial context

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

    Numbers at the beginning of a year

    np_acts-logits-general · gemini-2.0-flash

    years and numbers

    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
     stessa
    -0.53
     stessi
    -0.52
    ьажоргаш
    -0.48
     conseguenze
    -0.45
     honom
    -0.44
     próprias
    -0.42
     internationaux
    -0.41
     foule
    -0.41
     varandra
    -0.41
     medes
    -0.40
    POSITIVE LOGITS
    fjspx
    0.82
    findpost
    0.80
     onCreateView
    0.68
    sizeCache
    0.67
    FXMLLoader
    0.65
     iſt
    0.65
    UnusedPrivate
    0.63
    ibatis
    0.61
    rungsseite
    0.61
     تضيفلها
    0.61
    Activations Density 0.248%

    No Known Activations