© 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. 4-GEMMASCOPE-RES-16K
    11. 11483
    Prev
    Next
    INDEX
    Explanations

    references to twins and twin-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.65
    isticated
    -0.51
    تفصیلات
    -0.48
     bows
    -0.47
    gucigalpa
    -0.46
     AppBar
    -0.45
    UrlResolution
    -0.44
    ungkinan
    -0.44
    hax
    -0.44
    xFFFFFFFF
    -0.44
    POSITIVE LOGITS
     twin
    1.94
     twins
    1.80
    twin
    1.70
    Twin
    1.70
     Twin
    1.63
     Twins
    1.62
    Twins
    1.56
     identical
    1.09
    孪
    1.04
     doppel
    1.02
    Activations Density 0.605%

    No Known Activations