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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11679
    Prev
    Next
    INDEX
    Explanations

    mentions of news sources or journalists reporting information

    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
    WithIOException
    -0.70
    richTextPanel
    -0.69
    httphttps
    -0.63
    出版年
    -0.57
    EDEFAULT
    -0.57
     nakalista
    -0.56
    IVEREF
    -0.55
    transQ
    -0.54
    postIndex
    -0.54
    AndEndTag
    -0.52
    POSITIVE LOGITS
     ObjectParameter
    0.37
     asynchronous
    0.32
     relays
    0.31
    ulkan
    0.30
     Ups
    0.30
    ambassade
    0.30
    ⋙
    0.29
     Oxidation
    0.28
    undi
    0.28
     biệt
    0.28
    Activations Density 0.114%

    No Known Activations