© 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. 4197
    Prev
    Next
    INDEX
    Explanations

    text related to statistical analysis or mathematical modeling

    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
     
    -0.69
    <eos>
    -0.63
     c
    -0.57
     R
    -0.54
     M
    -0.53
     P
    -0.52
    ;
    -0.52
     a
    -0.51
     G
    -0.51
     F
    -0.51
    POSITIVE LOGITS
    AndEndTag
    1.35
    awtextra
    1.34
     NSCoder
    1.29
    ContentAsync
    1.29
    featureID
    1.28
     bezeichneter
    1.27
    setVerticalGroup
    1.27
     Мексичка
    1.26
    webElementXpaths
    1.25
     AssemblyTitle
    1.24
    Activations Density 2.600%

    No Known Activations