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. 20-GEMMASCOPE-RES-16K
    6. 2474
    Prev
    Next
    INDEX
    Explanations

    references to candy and confectionery products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    candy and chocolate

    np_acts-logits-general · gemini-2.0-flash

    candy and chocolate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.61
    GOTREF
    -0.61
     OnInit
    -0.59
    alnız
    -0.58
    nyard
    -0.56
    ulkner
    -0.56
     Hệ
    -0.56
     yurt
    -0.54
     gills
    -0.54
     Granger
    -0.53
    POSITIVE LOGITS
     candy
    1.70
     chocolate
    1.60
     chocolates
    1.43
     candies
    1.40
    candy
    1.34
     Chocolate
    1.31
    chocolate
    1.30
     Candy
    1.28
    Chocolate
    1.27
     sweets
    1.25
    Activations Density 0.152%

    No Known Activations