© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 12026
    Prev
    Next
    INDEX
    Explanations

    phrases related to recovery and restoration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hearsed
    -0.46
    printLine
    -0.45
     procrastination
    -0.44
     Subtract
    -0.44
    strando
    -0.44
     lateinit
    -0.44
    pushFollow
    -0.43
    قيقة
    -0.42
    AndEndTag
    -0.40
     sürekli
    -0.40
    POSITIVE LOGITS
     restored
    2.21
     return
    2.16
     regained
    2.10
     returning
    2.08
     reinstated
    2.07
     reinstatement
    2.05
     returned
    2.04
     regaining
    2.03
     regain
    2.03
     restoring
    2.00
    Activations Density 1.013%

    No Known Activations