© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 9211
    Prev
    Next
    INDEX
    Explanations

    elements related to instructions and technical specifications in a context involving equipment or product support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
     ujednoznacz
    -0.83
     Chwiliwch
    -0.72
     EconPapers
    -0.72
     незавершена
    -0.72
    protoimpl
    -0.70
     Mestre
    -0.66
    ContentAsync
    -0.65
    Portály
    -0.65
     Riproduzione
    -0.65
     mineures
    -0.64
    POSITIVE LOGITS
    rodow
    0.52
     thiệu
    0.52
    ngdoc
    0.49
    Gambas
    0.49
     SqlCommand
    0.46
     на
    0.43
    Batis
    0.43
    elerik
    0.43
    glUniform
    0.42
    SqlClient
    0.42
    Activations Density 0.080%

    No Known Activations