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. 5-GEMMASCOPE-RES-16K
    6. 1418
    Prev
    Next
    INDEX
    Explanations

    mentions of the color yellow and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.99
    __*/
    -0.95
    yntaxException
    -0.81
    PostConstruct
    -0.81
    AnchorTagHelper
    -0.78
    makeConstraints
    -0.78
     restTemplate
    -0.77
     Winaray
    -0.76
     propOrder
    -0.75
    <%=
    -0.71
    POSITIVE LOGITS
     Yellow
    2.24
     yellow
    2.14
    Yellow
    2.13
     YELLOW
    2.00
    yellow
    1.89
    YELLOW
    1.74
     yellows
    1.56
     jaune
    1.44
     yellowish
    1.33
    黄
    1.26
    Activations Density 0.047%

    No Known Activations