© 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. 3-GEMMASCOPE-RES-16K
    11. 9677
    Prev
    Next
    INDEX
    Explanations

    different forms of the word "edit" or variations of words that imply editing or modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InSection
    -0.60
    webElementXpaths
    -0.56
    الإنجليزية
    -0.55
    AddTagHelper
    -0.54
    mybatisplus
    -0.51
    цездатний
    -0.51
    Географиясе
    -0.50
    avaş
    -0.49
     gouvernements
    -0.48
     féd
    -0.47
    POSITIVE LOGITS
    muş
    0.65
    된
    0.62
    cted
    0.61
    एको
    0.61
     localObject
    0.61
    Portale
    0.61
    ATED
    0.60
    miş
    0.60
    ised
    0.60
    ated
    0.59
    Activations Density 0.313%

    No Known Activations