© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30448
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proximity or connection between subjects in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prepositions followed by determiners or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -1.00
     autorytatywna
    -0.85
    LabelTagHelper
    -0.72
    ]--;
    -0.72
    rawDesc
    -0.71
    setVerticalGroup
    -0.69
    исленность
    -0.66
    PerformLayout
    -0.66
    DeleteBehavior
    -0.66
     viewDidLoad
    -0.64
    POSITIVE LOGITS
     it
    0.52
     uten
    0.50
     hebdomada
    0.46
     ويكيميديا
    0.45
    ={({
    0.45
     something
    0.45
     Pi
    0.44
     borde
    0.44
     stuff
    0.43
    摇
    0.43
    Activations Density 0.122%

    No Known Activations