© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 16896
    Prev
    Next
    INDEX
    Explanations

    the presence of paragraph or section markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.69
     preocupação
    -0.61
     Exactos
    -0.59
    LookAnd
    -0.58
     väli
    -0.57
     esimer
    -0.56
    олові
    -0.55
    fillText
    -0.53
     riport
    -0.53
     jLabel
    -0.53
    POSITIVE LOGITS
    Revenir
    2.13
    AntiForgeryToken
    1.98
    ConstraintMaker
    1.80
     referenties
    1.71
    Hochspringen
    1.55
    Skocz
    1.42
     EconPapers
    1.24
    Capítulo
    1.23
     通販
    1.16
    Lähteet
    1.02
    Activations Density 0.000%

    No Known Activations