© 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. 2-GEMMASCOPE-RES-16K
    11. 8660
    Prev
    Next
    INDEX
    Explanations

    mentions of collaboration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ReactDOM
    -0.46
    termilk
    -0.41
    неопр
    -0.41
    setupUi
    -0.41
    #
    -0.39
    iNdEx
    -0.39
     onStart
    -0.39
    不錯
    -0.39
     vs
    -0.38
    さすがに
    -0.38
    POSITIVE LOGITS
     computing
    0.63
    expandindo
    0.60
     Computing
    0.59
     collective
    0.59
    cont
    0.57
     contributions
    0.56
     settlement
    0.55
     cont
    0.54
     Cont
    0.54
     counting
    0.54
    Activations Density 0.160%

    No Known Activations