© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16-GEMMASCOPE-RES-16K
    11. 13612
    Prev
    Next
    INDEX
    Explanations

    text related to ethical dilemmas and moral conflict

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

    Comes before "because" or "as"

    np_acts-logits-general · gemini-2.0-flash

    providing reasons or justifications

    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
     defaultstate
    -0.84
     дописавши
    -0.75
     بيها
    -0.66
    RegressionTest
    -0.61
     transférez
    -0.60
     jScrollPane
    -0.58
     '\\;'
    -0.56
     tolerancia
    -0.55
    enschappe
    -0.54
    ỡng
    -0.54
    POSITIVE LOGITS
     lest
    0.77
     would
    0.75
    Too
    0.71
     too
    0.67
     Too
    0.67
    too
    0.66
     fear
    0.63
    would
    0.63
     risk
    0.62
     Would
    0.60
    Activations Density 0.420%

    No Known Activations