© 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. 21-GEMMASCOPE-RES-16K
    11. 1852
    Prev
    Next
    INDEX
    Explanations

    references to combinations and mixtures of compounds or materials in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.81
     Normdatei
    -0.81
     pinulongan
    -0.76
    ValueStyle
    -0.68
     StatefulWidget
    -0.67
    +#+#
    -0.66
    IsMutable
    -0.66
    httphttps
    -0.64
    __(/*!
    -0.63
    BagLayout
    -0.61
    POSITIVE LOGITS
     thereof
    2.90
     thereto
    2.15
     therefrom
    1.98
     thereon
    1.97
     therefor
    1.87
     therein
    1.81
     therewith
    1.81
     daarvan
    1.62
     thereunder
    1.55
     hereof
    1.47
    Activations Density 0.594%

    No Known Activations