© 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. 20-GEMMASCOPE-RES-16K
    11. 5742
    Prev
    Next
    INDEX
    Explanations

    references to belonging and placement within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "belong" or its variations

    np_acts-logits-general · gemini-2.0-flash

    belonging somewhere or to something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unmodifiable
    -0.59
    !*\
    -0.56
     censiti
    -0.53
    fattning
    -0.51
     available
    -0.48
    available
    -0.47
    ībā
    -0.47
    Available
    -0.46
    WARE
    -0.44
     Available
    -0.44
    POSITIVE LOGITS
     belong
    1.87
     belongs
    1.80
     belonged
    1.72
    belong
    1.59
    belongs
    1.53
     Belong
    1.35
     belonging
    1.23
     pertence
    1.16
     patří
    1.12
     pertenece
    1.11
    Activations Density 0.215%

    No Known Activations