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. 3-GEMMASCOPE-RES-16K
    6. 10842
    Prev
    Next
    INDEX
    Explanations

    references to diagnostic codes and classifications in the medical field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.59
    :✨
    -0.54
    Datuak
    -0.48
    expects
    -0.47
    viewtopic
    -0.46
    Docket
    -0.45
    IsContent
    -0.43
    ]=="
    -0.43
    osho
    -0.42
    Numerology
    -0.42
    POSITIVE LOGITS
     Normdatei
    0.82
    neſs
    0.73
     purpoſe
    0.71
     Majefty
    0.71
     quæ
    0.69
    ſelf
    0.69
     perſon
    0.69
    IMPORTED
    0.68
     houſe
    0.66
     pleaſure
    0.66
    Activations Density 0.711%

    No Known Activations