© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15314
    Prev
    Next
    INDEX
    Explanations

    terms specifically related to interpersonal relationships and their dynamics

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

    "relationships."

    np_acts-logits-general · gemini-2.0-flash

    relationships and partnerships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fufficient
    -0.62
     ſta
    -0.60
     Aleg
    -0.59
     ſmall
    -0.59
    Jegyzetek
    -0.58
    Gele
    -0.58
    eroy
    -0.57
    TestingModule
    -0.57
     reafon
    -0.57
     raisonnable
    -0.57
    POSITIVE LOGITS
     relationships
    0.88
     relationship
    0.86
    Relationships
    0.76
     Relationship
    0.70
     Relationships
    0.69
     Beziehungen
    0.68
    relationships
    0.66
     bonds
    0.63
     bond
    0.60
    Relationship
    0.60
    Activations Density 0.186%

    No Known Activations