© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1102
    Prev
    Next
    INDEX
    Explanations

    terms related to emotional intelligence and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.75
     PhpStorm
    -0.67
    setVerticalGroup
    -0.65
     EconPapers
    -0.62
    Portale
    -0.60
    <eos>
    -0.58
     noqa
    -0.58
     javafx
    -0.58
     transférez
    -0.57
    EqualsAnd
    -0.56
    POSITIVE LOGITS
     '\\;'
    0.71
     تضيفلها
    0.69
     calendriers
    0.64
    eleste
    0.59
     Privilege
    0.52
    曖昧さ回避
    0.52
    ubel
    0.50
    Zeneca
    0.49
    jointe
    0.48
    asteroide
    0.47
    Activations Density 0.586%

    No Known Activations