© 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. 23-GEMMASCOPE-RES-16K
    11. 9916
    Prev
    Next
    INDEX
    Explanations

    sentences that begin with "So," indicating a conversational or explanatory tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quarter
    -0.33
     “
    -0.32
     three
    -0.31
     precedentes
    -0.31
    OrBuilder
    -0.31
    ализация
    -0.29
     x
    -0.29
     مذه
    -0.28
     two
    -0.28
     |
    -0.28
    POSITIVE LOGITS
    :✨
    0.76
     propOrder
    0.75
     Normdatei
    0.69
    ViewImports
    0.64
    出版年
    0.64
    bootstrapcdn
    0.59
     ſind
    0.55
    mybatisplus
    0.55
    点此举报
    0.55
    WithIOException
    0.54
    Activations Density 0.197%

    No Known Activations