© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7272
    Prev
    Next
    INDEX
    Explanations

    connections to databases and related operations in code

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

    Database or client connections

    np_acts-logits-general · gemini-2.0-flash

    connection or connect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.69
    ädie
    -0.59
    erover
    -0.55
     ModelAndView
    -0.55
    ẨM
    -0.55
     ModelRenderer
    -0.53
     Paredes
    -0.53
     Processors
    -0.53
    werth
    -0.53
     exhaust
    -0.52
    POSITIVE LOGITS
     connection
    1.05
     Connection
    0.98
    connect
    0.94
    connection
    0.94
    Connection
    0.94
     connections
    0.90
     connect
    0.89
    Connect
    0.86
     CONNECTION
    0.85
    createConnection
    0.85
    Activations Density 0.165%

    No Known Activations