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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12918
    Prev
    Next
    INDEX
    Explanations

    expressions related to legal and ethical discussions in political contexts

    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
    TagMode
    -0.55
    !&
    -0.55
    olique
    -0.51
    责任编辑
    -0.50
    /$',
    -0.50
    .}}
    -0.48
     EconPapers
    -0.47
     included
    -0.47
    \|_{\
    -0.47
    Открыть
    -0.46
    POSITIVE LOGITS
    <blockquote>
    2.63
    <code>
    0.68
     initComponents
    0.67
     AspNetCore
    0.66
    ":
    
    0.65
    LookAnd
    0.58
    CloseOperation
    0.57
    ':
    
    0.56
    </blockquote>
    0.56
     onCreateView
    0.56
    Activations Density 0.095%

    No Known Activations