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. 1-GEMMASCOPE-RES-16K
    6. 9901
    Prev
    Next
    INDEX
    Explanations

    references to rice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rcpp
    -0.68
    darwin
    -0.61
    lyk
    -0.58
    Soorten
    -0.58
    kait
    -0.56
    knex
    -0.56
    nungs
    -0.56
     uska
    -0.56
    momentum
    -0.53
    seasonal
    -0.53
    POSITIVE LOGITS
     sacrifice
    1.02
     sacrificing
    0.94
     sacrifices
    0.94
     sacrificed
    0.91
     rice
    0.91
     Sacrifice
    0.89
    sacrifice
    0.84
     sacrific
    0.79
    Rice
    0.75
    出版年
    0.72
    Activations Density 0.050%

    No Known Activations