© 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. 38340
    Prev
    Next
    INDEX
    Explanations

    occurrences of the German word "ein" and its variations, indicating a focus on articles or quantifiers

    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
     MainAxisSize
    -0.92
    RenderAtEndOf
    -0.91
    Berikut
    -0.91
     Nunn
    -0.91
    ViewFeatures
    -0.88
    abestanden
    -0.88
     Ouverture
    -0.88
    QMetaType
    -0.87
     Romagna
    -0.87
    XmlAccessorType
    -0.85
    POSITIVE LOGITS
     Ein
    1.17
    Ein
    1.02
     ein
    0.99
     EIN
    0.94
     Sein
    0.84
    uParam
    0.81
     STEIN
    0.77
    ein
    0.72
    skine
    0.71
    tein
    0.71
    Activations Density 0.006%

    No Known Activations