Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11440
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols related to programming, statistics, and mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.63
    expandindo
    -0.61
    SourceChecksum
    -0.59
    tangentMode
    -0.58
     Италијани
    -0.55
    adaptiveStyles
    -0.54
    󠁴
    -0.54
    Abitanti
    -0.53
     IFTT
    -0.51
     ProtoMessage
    -0.51
    POSITIVE LOGITS
     Paglinawan
    0.78
     للمعارف
    0.74
    Obrázky
    0.68
     ostavi
    0.65
    Tembelea
    0.59
    ьаж
    0.57
    abstractmethod
    0.56
    writeField
    0.55
     typelib
    0.53
     Вікіпе
    0.53
    Activations Density 5.362%

    No Known Activations