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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5207
    Prev
    Next
    INDEX
    Explanations

    references to stores and shopping experiences related to fabric and crafts

    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
     GenerationType
    -0.51
    SourceChecksum
    -0.50
    EDEFAULT
    -0.48
    verwijspagina
    -0.45
    GEBURTSDATUM
    -0.42
    WaitGroup
    -0.42
     EconPapers
    -0.41
    __':
    
    -0.40
    ValueGeneration
    -0.39
    RunWith
    -0.39
    POSITIVE LOGITS
     store
    0.73
    store
    0.65
    STORE
    0.64
    Store
    0.64
     Store
    0.63
     stocking
    0.63
     stores
    0.62
     retailer
    0.61
     sales
    0.59
     purchases
    0.59
    Activations Density 0.164%

    No Known Activations