© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 2792
    Prev
    Next
    INDEX
    Explanations

    emotional responses and reactions related to social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.75
     linkovi
    -0.74
    ftagPool
    -0.70
    findpost
    -0.65
    __(/*!
    -0.63
    Autoritní
    -0.63
    BeginInit
    -0.63
     Efq
    -0.61
     cherchés
    -0.60
     متعلقه
    -0.59
    POSITIVE LOGITS
    XmlRootElement
    0.48
     diagon
    0.46
    edb
    0.46
    COUVER
    0.46
    OfWeek
    0.44
    ungszeit
    0.43
     NUKAT
    0.43
    IVEREF
    0.42
     leave
    0.41
     руку
    0.41
    Activations Density 0.069%

    No Known Activations