© 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. 3-GEMMASCOPE-RES-16K
    11. 3153
    Prev
    Next
    INDEX
    Explanations

    terms related to establishing and maintaining connections, particularly in a programming or network context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
     Terraria
    -0.68
    ViewFeatures
    -0.66
    mäßigen
    -0.65
     knex
    -0.63
     UIImage
    -0.61
    aVar
    -0.61
    bitField
    -0.60
     Gleaner
    -0.60
    RepeatedField
    -0.59
    POSITIVE LOGITS
    connect
    2.33
     Connect
    2.20
    Connect
    2.18
     connect
    1.90
     CONNECT
    1.78
    CONNECT
    1.76
     connects
    1.48
    connects
    1.36
     connecting
    1.34
    Connecting
    1.32
    Activations Density 0.092%

    No Known Activations