© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8928
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss the contrast between rational and emotional decision-making

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

    Contrasting science/data with feelings/humanities

    np_acts-logits-general · gemini-2.0-flash

    gut feelings vs objective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sober
    -0.40
    twimg
    -0.38
    deaf
    -0.36
    autoconfigure
    -0.36
     Allein
    -0.35
    zarchiwizowane
    -0.35
     seco
    -0.35
    WebElementEntity
    -0.35
    提
    -0.34
     métallique
    -0.34
    POSITIVE LOGITS
     emotional
    0.82
     qualitative
    0.79
    emotional
    0.77
     humanistic
    0.77
     humanities
    0.74
     softer
    0.73
     subjective
    0.69
     recreational
    0.68
     informal
    0.68
     emocional
    0.67
    Activations Density 0.760%

    No Known Activations