© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 12570
    Prev
    Next
    INDEX
    Explanations

    references to development frameworks or libraries, particularly related to mobile applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rayures
    -0.62
     carreaux
    -0.54
    STATEMENT
    -0.54
    FOOTNOTES
    -0.53
     statement
    -0.53
     meubles
    -0.53
     lèvres
    -0.51
    råd
    -0.51
     betale
    -0.51
     tourner
    -0.51
    POSITIVE LOGITS
    addComponent
    1.36
     QtWidgets
    1.24
    PerformLayout
    1.22
     StatelessWidget
    1.19
    EndInit
    1.17
    BeginInit
    1.12
    AccessorTable
    1.05
     QtGui
    1.04
     StatefulWidget
    1.04
    addGroup
    1.03
    Activations Density 0.004%

    No Known Activations