© 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. 10610
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formatting in written content

    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
    WriteTagHelper
    -0.83
     resourceCulture
    -0.69
     مشين
    -0.65
    addCriterion
    -0.63
    "}}
    -0.61
    argento
    -0.59
     AssemblyTitle
    -0.58
    expandindo
    -0.55
     connexes
    -0.55
    Portail
    -0.55
    POSITIVE LOGITS
     surla
    0.82
     HttpServlet
    0.65
    ieteur
    0.60
    addWidget
    0.60
     Loth
    0.59
    kug
    0.58
    noopener
    0.56
    icoot
    0.56
     oraciones
    0.55
    URLException
    0.55
    Activations Density 0.079%

    No Known Activations