© 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. 4-GEMMASCOPE-RES-16K
    11. 4196
    Prev
    Next
    INDEX
    Explanations

    references to specific brands, products, technologies, or popular culture elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.62
    gjenge
    -0.56
    lwjgl
    -0.54
     echter
    -0.54
    zczegól
    -0.53
    ymmetric
    -0.53
    amese
    -0.53
    allax
    -0.53
    testng
    -0.53
    <#
    -0.52
    POSITIVE LOGITS
    Naissance
    0.66
    瘍
    0.65
    windowFixed
    0.65
     betweenstory
    0.55
     vapours
    0.53
    bitField
    0.51
    assination
    0.51
    UrlResolution
    0.51
    asants
    0.50
     imprisonment
    0.49
    Activations Density 4.160%

    No Known Activations