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. 15-GEMMASCOPE-RES-16K
    6. 2388
    Prev
    Next
    INDEX
    Explanations

    terms related to product durability and reliability in the context of appliances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ticias
    -0.51
    — 
    -0.50
    ंदीखरीदारी
    -0.49
    <bos>
    -0.48
      (
    -0.48
    zupeł
    -0.45
    faker
    -0.45
    PhysRev
    -0.43
    ובה
    -0.43
    tiba
    -0.43
    POSITIVE LOGITS
     durability
    1.05
     Durability
    0.91
     durable
    0.84
     longevity
    0.77
     lifetime
    0.76
    durable
    0.76
     durabilidad
    0.75
    Durability
    0.75
    lifetime
    0.72
     Durable
    0.72
    Activations Density 0.180%

    No Known Activations