© 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. 1-GEMMASCOPE-RES-16K
    11. 2609
    Prev
    Next
    INDEX
    Explanations

    references to networks or systems related to information exchange

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🟤
    -0.38
    ſt
    -0.33
    बाइल
    -0.31
    Geplaatst
    -0.31
     jul
    -0.30
     james
    -0.29
     reg
    -0.29
    付
    -0.29
    FFFFFF
    -0.29
    Сообщение
    -0.29
    POSITIVE LOGITS
     network
    1.02
     networks
    0.90
     NSCoder
    0.84
     knock
    0.81
    network
    0.81
     Network
    0.81
     NETWORK
    0.81
     knocks
    0.79
    ंदीखरीदारी
    0.77
     réseau
    0.76
    Activations Density 0.151%

    No Known Activations