© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5479
    Prev
    Next
    INDEX
    Explanations

    connections to legal and health-related terms and issues

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

    Followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    future predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     betweenstory
    -0.71
     препратки
    -0.69
     AssemblyCulture
    -0.68
    WithIOException
    -0.66
     propOrder
    -0.62
    richTextPanel
    -0.60
    RTLI
    -0.59
     للمعارف
    -0.56
    RTRS
    -0.56
     ویکی‌پدیا
    -0.55
    POSITIVE LOGITS
    enumi
    0.47
    IUrlHelper
    0.44
     Dafür
    0.39
    Ĝ
    0.36
     via
    0.32
     fixé
    0.31
     capitalize
    0.31
     using
    0.31
    using
    0.30
     note
    0.30
    Activations Density 1.095%

    No Known Activations