© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11741
    Prev
    Next
    INDEX
    Explanations

    special beginnings or indicators in programming or markup structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GTCX
    -0.56
     Italijani
    -0.56
    moveToFirst
    -0.55
     الرياضيه
    -0.54
     BitmapFactory
    -0.54
    setopt
    -0.53
    龇
    -0.52
     defStyleAttr
    -0.52
    TemporalType
    -0.51
     CoreData
    -0.50
    POSITIVE LOGITS
     [*]
    1.00
    
    0.71
    TagMode
    0.68
    filepath
    0.65
     noDo
    0.60
    RegressionTest
    0.55
    /***/
    0.55
     ExecuteAsync
    0.50
    tagHelperRunner
    0.50
    出版年
    0.49
    Activations Density 0.120%

    No Known Activations