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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5079
    Prev
    Next
    INDEX
    Explanations

    references to life and its various dimensions, including satisfaction, planning, and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McGregor
    -0.50
    queiro
    -0.48
    bildeten
    -0.48
    retudo
    -0.47
     couronne
    -0.46
     brewers
    -0.46
     Crom
    -0.46
     amarelo
    -0.46
     terceira
    -0.46
     comerciais
    -0.45
    POSITIVE LOGITS
    life
    1.26
    Life
    1.25
    LIFE
    1.23
     LIFE
    1.19
     Life
    1.13
     life
    1.11
    lifes
    1.00
    Lif
    0.93
     lifes
    0.85
     vida
    0.84
    Activations Density 0.067%

    No Known Activations