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. 4792
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to second-hand goods and their quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    PMailer
    -0.55
    XMLHttpRequest
    -0.46
    itettura
    -0.44
    ruptive
    -0.42
    ッケージ
    -0.42
    copg
    -0.41
    itoral
    -0.41
     absence
    -0.41
    piew
    -0.41
    leistungs
    -0.41
    POSITIVE LOGITS
     secondhand
    1.47
     Used
    1.07
    二手
    1.06
     used
    1.06
     resale
    1.05
     refurbished
    1.05
    Used
    1.05
    中古
    1.04
     second
    1.02
     gebraucht
    1.02
    Activations Density 0.136%

    No Known Activations