© 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. 9649
    Prev
    Next
    INDEX
    Explanations

    proximity-related expressions and sentiments

    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
     Référence
    -0.54
    ulose
    -0.53
    ankara
    -0.53
    ագրություններ
    -0.51
     Rot
    -0.50
    elum
    -0.49
     vidare
    -0.49
     geslacht
    -0.48
    ंबर
    -0.48
     Völ
    -0.47
    POSITIVE LOGITS
     closer
    1.63
     close
    1.55
    closer
    1.43
     proximity
    1.39
     Closer
    1.36
     nearer
    1.35
     closeness
    1.34
     Close
    1.31
     closest
    1.29
     CLOSE
    1.29
    Activations Density 0.366%

    No Known Activations