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. 21-GEMMASCOPE-RES-16K
    6. 12482
    Prev
    Next
    INDEX
    Explanations

    references to social relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    妻
    -0.77
     Ms
    -0.77
    妻子
    -0.76
     istrinya
    -0.75
    Ms
    -0.70
    老婆
    -0.70
    彼女
    -0.68
     koji
    -0.66
    女友
    -0.65
     wife
    -0.64
    POSITIVE LOGITS
     herself
    1.36
     husband
    1.11
     husbands
    1.02
     suaminya
    0.99
    herself
    0.98
    husband
    0.98
     boyfriends
    0.94
     chồng
    0.90
     Husband
    0.88
     motherhood
    0.87
    Activations Density 0.493%

    No Known Activations