Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12723
    Prev
    Next
    INDEX
    Explanations

    concepts related to social interactions and relationships

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

    Preceding "people"

    np_acts-logits-general · gemini-2.0-flash

    people and friends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Filmographie
    -0.68
     utafitiHapana
    -0.66
    />";
    -0.62
    Patient
    -0.60
     Signalez
    -0.60
     Employee
    -0.60
    
    -0.59
    ighed
    -0.59
     Patient
    -0.59
     Player
    -0.59
    POSITIVE LOGITS
     people
    3.38
    people
    2.50
    People
    2.17
     PEOPLE
    2.03
     People
    2.02
     mensen
    1.96
     ppl
    1.76
     pessoas
    1.71
     peop
    1.68
     peo
    1.68
    Activations Density 0.454%

    No Known Activations