© 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. 4-GEMMASCOPE-RES-16K
    11. 9660
    Prev
    Next
    INDEX
    Explanations

    preferences expressed through the phrase "I would rather."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jspx
    -0.75
    AndEndTag
    -0.72
    tagHelper
    -0.65
    /*
    -0.65
    elemField
    -0.63
    twimg
    -0.61
    //
    -0.61
    saraba
    -0.61
    TagHelper
    -0.61
     calendriers
    -0.60
    POSITIVE LOGITS
     préfère
    1.10
     prefer
    1.07
     préfé
    0.98
    prefer
    0.94
     prefers
    0.93
     prefi
    0.90
     preferring
    0.89
     liever
    0.89
     prefier
    0.88
    Prefer
    0.87
    Activations Density 0.243%

    No Known Activations