© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5514
    Prev
    Next
    INDEX
    Explanations

    the term "being" in various contexts

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

    Following the word "Being"

    np_acts-logits-general · gemini-2.0-flash

    Being followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addContainerGap
    -0.61
    laughing
    -0.60
     Perkins
    -0.59
     Karsten
    -0.57
    </b>
    -0.56
    clu
    -0.54
    Cuts
    -0.53
    <b>
    -0.52
     aeruginosa
    -0.52
    DoubleQuotes
    -0.51
    POSITIVE LOGITS
    FieldBuilder
    1.00
    DeleteBehavior
    0.75
    CodedInputStream
    0.74
     referenties
    0.70
     Orrell
    0.70
    ly
    0.68
    APORE
    0.68
     ostavi
    0.66
    viola
    0.66
    ness
    0.65
    Activations Density 0.145%

    No Known Activations