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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4641
    Prev
    Next
    INDEX
    Explanations

    demographics related to specific age and gender groups

    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
     initComponents
    -0.51
    سطس
    -0.51
    omia
    -0.50
    cstdlib
    -0.50
    muth
    -0.49
    Portale
    -0.49
     safe
    -0.49
     mergeFrom
    -0.48
     Réalisation
    -0.47
    nilai
    -0.47
    POSITIVE LOGITS
    Obrázky
    0.67
    HttpPut
    0.59
    cyd
    0.58
     cerevisiae
    0.55
    Datuak
    0.51
     väli
    0.49
    المناصب
    0.49
     ostavi
    0.48
    ք
    0.48
    ESTR
    0.48
    Activations Density 0.277%

    No Known Activations