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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13971
    Prev
    Next
    INDEX
    Explanations

    references to specific technology companies and their products or services

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

    the company "Apple"

    np_acts-logits-general · gemini-2.0-flash

    Apple company and products

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    beitrag
    -0.43
     Vorsitzende
    -0.39
     Weid
    -0.38
     partecipare
    -0.35
     Vorsitzender
    -0.35
     vestito
    -0.34
     intptr
    -0.34
     beroep
    -0.34
     verzorg
    -0.33
     پذ
    -0.33
    POSITIVE LOGITS
     Apple
    1.02
    Apple
    1.00
     Cupertino
    0.85
     iPhones
    0.80
     apple
    0.80
     iCloud
    0.78
     macOS
    0.77
     iPhone
    0.77
     SwiftUI
    0.76
     للاسماء
    0.75
    Activations Density 0.322%

    No Known Activations