© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 144
    Prev
    Next
    INDEX
    Explanations

    features related to social media account integration and online platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Social media platforms or online marketplaces

    np_acts-logits-general · gemini-2.0-flash

    online platforms and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.82
    Становништво
    -0.71
     BoxFit
    -0.68
    RetentionPolicy
    -0.66
    ($__
    -0.65
    脚注の使い方
    -0.63
    nonatomic
    -0.63
    
    -0.61
     BoxDecoration
    -0.60
    BeginContext
    -0.60
    POSITIVE LOGITS
     Google
    1.52
     Facebook
    1.45
     Amazon
    1.40
     YouTube
    1.32
    Google
    1.30
     Instagram
    1.21
     google
    1.20
    Facebook
    1.18
     Youtube
    1.16
    Amazon
    1.14
    Activations Density 0.365%

    No Known Activations