© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10129
    Prev
    Next
    INDEX
    Explanations

    verbs that suggest the process of creating or changing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.68
     <>",
    -0.66
     ब्रेकडाउन
    -0.55
    uxxxx
    -0.55
    mapStateToProps
    -0.53
    reportWebVitals
    -0.52
     שוליים
    -0.48
     CascadeType
    -0.46
    Mutagenicity
    -0.45
    怎么了
    -0.45
    POSITIVE LOGITS
     gøre
    0.56
     accesibles
    0.54
     accessibility
    0.52
    easier
    0.49
     rendu
    0.49
     gjort
    0.48
     accessible
    0.47
     accesible
    0.47
     easier
    0.47
     gjøre
    0.47
    Activations Density 0.362%

    No Known Activations