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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15686
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to durability and longevity in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ivelany
    -0.59
    出版年
    -0.58
     linkovi
    -0.51
    Apis
    -0.51
     незавершена
    -0.51
    気味
    -0.50
     neceff
    -0.50
    BeginContext
    -0.48
     lizenz
    -0.47
    ophora
    -0.47
    POSITIVE LOGITS
     withstand
    1.71
     durability
    1.49
     survive
    1.43
     survives
    1.41
     durable
    1.40
     survived
    1.40
     resist
    1.39
     resists
    1.38
     lasts
    1.36
     lasted
    1.34
    Activations Density 0.350%

    No Known Activations