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. 0-GEMMASCOPE-RES-16K
    6. 2332
    Prev
    Next
    INDEX
    Explanations

    references to T-helper cells (Th cells) in the context of immune responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reſ
    -0.64
     Anſ
    -0.59
     houſe
    -0.59
     retrie
    -0.59
    WEBPACK
    -0.58
    сылкі
    -0.57
     Jop
    -0.56
    expandindo
    -0.56
     itſelf
    -0.56
     neceff
    -0.56
    POSITIVE LOGITS
     Th
    0.69
     Wu
    0.64
    ima
    0.62
    IMA
    0.61
    省市镇
    0.58
     chi̍t
    0.58
    AxisAlignment
    0.58
     And
    0.58
    hasMoreElements
    0.58
    ToListAsync
    0.57
    Activations Density 0.128%

    No Known Activations