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. 21-GEMMASCOPE-RES-16K
    6. 2931
    Prev
    Next
    INDEX
    Explanations

    descriptions of diverse cultural influences and attractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.82
     nahilalakip
    -0.63
     betweenstory
    -0.61
    hyrchwyd
    -0.60
    IContainer
    -0.59
    SharedCtor
    -0.59
     AspNetCore
    -0.57
    atchewan
    -0.56
    DotNetBar
    -0.55
    tanleria
    -0.55
    POSITIVE LOGITS
     attract
    2.38
     attraction
    2.30
     attracts
    2.22
     attracting
    2.19
     Attra
    2.17
     appeal
    2.17
    Attra
    2.15
     lure
    2.14
     attracted
    2.12
    attra
    2.03
    Activations Density 0.371%

    No Known Activations