© 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. 11328
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles related to ongoing actions

    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
    ')],
    -0.77
     cauſe
    -0.76
    bonucleic
    -0.73
     Administrativna
    -0.72
     [],
    -0.72
    "]];
    -0.71
     purpoſe
    -0.67
     itſelf
    -0.67
    躇
    -0.66
    InstrumentedTest
    -0.66
    POSITIVE LOGITS
     having
    1.16
     taking
    1.09
     getting
    1.07
     using
    1.05
     enjoying
    1.02
     being
    1.02
     trying
    0.97
     realising
    0.97
     making
    0.95
     delivering
    0.94
    Activations Density 0.399%

    No Known Activations