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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3326
    Prev
    Next
    INDEX
    Explanations

    phrases and keywords related to costs and pricing

    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
    resave
    -0.42
     Residences
    -0.35
    Biografi
    -0.35
     Justiça
    -0.34
    cierre
    -0.33
     Baked
    -0.33
    zellan
    -0.32
    éli
    -0.32
     lão
    -0.31
     gestire
    -0.30
    POSITIVE LOGITS
     price
    0.66
     costs
    0.63
     inexpensive
    0.62
     priced
    0.62
     cheaper
    0.62
     biaya
    0.61
    price
    0.60
     cost
    0.60
    价格
    0.59
     costing
    0.59
    Activations Density 0.342%

    No Known Activations