© 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. 28-GEMMASCOPE-RES-16K
    11. 7814
    Prev
    Next
    INDEX
    Explanations

    references to internet connectivity issues and routers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Networking and internet configuration

    np_acts-logits-general · gemini-2.0-flash

    network configuration and security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    țional
    -0.36
     Uch
    -0.31
    ッキ
    -0.30
    Unload
    -0.30
    reco
    -0.29
     Cad
    -0.29
     maisha
    -0.29
     hangers
    -0.29
    lcd
    -0.29
    สัม
    -0.29
    POSITIVE LOGITS
     Internet
    0.93
     internet
    0.89
    Internet
    0.87
     router
    0.84
    internet
    0.83
     AssemblyCulture
    0.82
     routers
    0.81
    INTERNET
    0.77
     Router
    0.77
     INTERNET
    0.77
    Activations Density 0.823%

    No Known Activations