Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-GEMMASCOPE-RES-16K
    6. 6411
    Prev
    Next
    INDEX
    Explanations

    references to clothing and fashion, particularly in a cultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BackStack
    -0.56
    TagMode
    -0.56
    깥
    -0.55
    MessageTagHelper
    -0.52
     Socks
    -0.50
     QUAL
    -0.48
     nonatomic
    -0.48
     piace
    -0.47
    pshots
    -0.47
    nonatomic
    -0.46
    POSITIVE LOGITS
     costume
    0.78
     costumes
    0.74
    :✨
    0.72
     cost
    0.69
     COST
    0.68
    cost
    0.67
    scriptcase
    0.66
    Cost
    0.62
     kost
    0.60
    costume
    0.59
    Activations Density 0.150%

    No Known Activations