© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103485
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and references to equations or variable definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.84
     يتيمه
    -0.83
    transQ
    -0.81
     queſta
    -0.78
     EconPapers
    -0.75
    expandindo
    -0.74
    AddTagHelper
    -0.69
    ſſung
    -0.69
    ésultats
    -0.68
     kaarangay
    -0.68
    POSITIVE LOGITS
     smlou
    0.34
     influencing
    0.34
     phrase
    0.33
     einst
    0.32
     popolari
    0.32
     luxo
    0.31
     Defensa
    0.31
     bal
    0.31
     berbahaya
    0.30
     cocaína
    0.30
    Activations Density 0.090%

    No Known Activations