© 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. 2-GEMMASCOPE-RES-16K
    11. 4879
    Prev
    Next
    INDEX
    Explanations

    words related to the management and operations of VPN sites in a network

    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
    la
    -0.54
    le
    -0.53
     markets
    -0.51
    lat
    -0.51
     lat
    -0.50
    ol
    -0.49
    ken
    -0.49
     boundaries
    -0.47
    mat
    -0.47
    ad
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.92
     propOrder
    0.89
    ratulations
    0.74
    rxjs
    0.72
    ExtendWith
    0.69
     nakalista
    0.69
    ftance
    0.67
    essages
    0.66
     виправивши
    0.66
     âmes
    0.66
    Activations Density 0.553%

    No Known Activations