© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5183
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to social behavior and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allAfrica
    -0.37
    CloseOperation
    -0.36
    娘娘
    -0.35
    unnitel
    -0.35
     operation
    -0.34
     har
    -0.33
    acheteur
    -0.33
     RESPONS
    -0.33
     text
    -0.32
     paper
    -0.32
    POSITIVE LOGITS
     socializing
    0.79
     socialize
    0.74
     насељу
    0.68
     soci
    0.66
     amitié
    0.64
    Interaction
    0.64
     sociala
    0.64
     Networking
    0.64
     Interaction
    0.63
    interact
    0.61
    Activations Density 0.368%

    No Known Activations