© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11240
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to definitions and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.45
     nakalista
    -0.45
    extAlignment
    -0.44
     uſe
    -0.44
    idiv
    -0.43
    sendRedirect
    -0.43
     érde
    -0.41
    ⓧ
    -0.40
    richTextPanel
    -0.40
     fallu
    -0.40
    POSITIVE LOGITS
     stands
    1.43
     denotes
    1.36
     represents
    1.23
     refers
    1.16
    stands
    1.13
     denote
    1.11
     stand
    1.09
     Stands
    1.07
     represent
    1.06
     stood
    1.05
    Activations Density 1.193%

    No Known Activations