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. 1-GEMMASCOPE-RES-16K
    6. 10196
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly focusing on husbands and sons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.67
    ̈́
    -0.60
    kwür
    -0.58
    Peny
    -0.56
    CodeAnalysis
    -0.56
    ible
    -0.55
     prés
    -0.54
    IRY
    -0.54
    вропей
    -0.54
    hots
    -0.53
    POSITIVE LOGITS
     son
    1.45
     sons
    1.22
     husband
    1.18
     dad
    1.07
    husband
    1.01
     gentleman
    1.00
     boyfriend
    0.98
     husbands
    0.93
     gentlemen
    0.92
     Husband
    0.90
    Activations Density 0.076%

    No Known Activations