© 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. 11-GEMMASCOPE-RES-16K
    11. 10184
    Prev
    Next
    INDEX
    Explanations

    phrases indicating joint actions or relationships between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onAnimation
    -0.71
    出版年
    -0.69
     typelib
    -0.68
     للمعارف
    -0.63
     pinulongan
    -0.62
    twimg
    -0.61
     defaultstate
    -0.58
    ništ
    -0.58
    ualmente
    -0.54
    toMatchSnapshot
    -0.54
    POSITIVE LOGITS
    他和
    0.40
    你和
    0.36
     aload
    0.35
    她和
    0.33
    WriteLiteral
    0.32
     collaborators
    0.31
    RunWith
    0.31
     collaborateurs
    0.31
     others
    0.30
    kenstock
    0.30
    Activations Density 0.479%

    No Known Activations