© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5425
    Prev
    Next
    INDEX
    Explanations

    words related to destinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     للاسماء
    -0.57
     Summary
    -0.56
     clarify
    -0.50
     summary
    -0.50
    Summary
    -0.50
     pinulongan
    -0.50
     AssemblyCulture
    -0.48
     clarifying
    -0.47
     незавершена
    -0.47
    WriteLiteral
    -0.47
    POSITIVE LOGITS
     destination
    2.72
    destination
    2.47
     Destination
    2.41
    Destination
    2.31
     destinations
    2.27
     Destinations
    2.00
     destino
    1.88
    destinations
    1.86
     destina
    1.74
    Destinations
    1.72
    Activations Density 0.086%

    No Known Activations