© 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. 9723
    Prev
    Next
    INDEX
    Explanations

    Arabic words or phrases indicating preference or choice

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

    Follows "Q:" or contains question words

    np_acts-logits-general · gemini-2.0-flash

    reading and development

    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
     defaultstate
    -0.80
     pinulongan
    -0.73
     تضيفلها
    -0.72
    WriteTagHelper
    -0.71
     كومونز
    -0.65
     NDEBUG
    -0.61
     SafeMath
    -0.61
     Roskov
    -0.60
    ướ
    -0.60
    الإنجليزية
    -0.60
    POSITIVE LOGITS
     بيها
    0.62
     therewith
    0.50
     thereof
    0.50
     therefrom
    0.49
     به
    0.47
     kepada
    0.45
     kepad
    0.44
     Therefore
    0.44
    着
    0.43
     therefor
    0.42
    Activations Density 0.009%

    No Known Activations