© 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. 1-GEMMASCOPE-RES-16K
    11. 10939
    Prev
    Next
    INDEX
    Explanations

    the word "belong" and its variations, indicating a focus on possession or membership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addPreferredGap
    -0.61
    INOIS
    -0.57
    stylers
    -0.56
    }{*}{
    -0.54
    深度
    -0.53
     Su
    -0.53
    žní
    -0.51
    varu
    -0.51
    encji
    -0.51
    pageX
    -0.50
    POSITIVE LOGITS
     belong
    1.36
     belongs
    1.29
     belonged
    1.22
    belong
    1.13
    belongs
    1.05
     belonging
    1.04
     Belong
    1.00
     appartiennent
    0.92
     pertence
    0.89
     apparti
    0.85
    Activations Density 0.061%

    No Known Activations