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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9581
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptions of work hours and pay rates in job listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     ArrayAdapter
    -0.66
     ModelExpression
    -0.65
    MLLoader
    -0.62
    /**
    -0.60
    
    -0.58
    日閲覧
    -0.57
    adə
    -0.56
    mobileqq
    -0.56
    脚注の使い方
    -0.56
    قایناقلار
    -0.56
    POSITIVE LOGITS
     hours
    1.30
    hours
    1.12
     Hours
    1.12
     shifts
    1.12
    Hours
    1.04
     overtime
    0.99
     Shifts
    0.98
     HOURS
    0.97
    shifts
    0.97
     shift
    0.92
    Activations Density 0.160%

    No Known Activations