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. 12-GEMMASCOPE-RES-16K
    6. 5193
    Prev
    Next
    INDEX
    Explanations

    references to specific immune cell markers and related terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.74
     Ous
    -0.69
     Verg
    -0.68
    fulness
    -0.68
    itanya
    -0.68
    clientY
    -0.67
     ATL
    -0.67
     Dever
    -0.66
    hous
    -0.64
    ǝ
    -0.64
    POSITIVE LOGITS
     CDs
    1.40
     CD
    1.29
     discs
    1.22
    CD
    1.21
     disks
    1.15
     cd
    1.12
    CDs
    1.05
    💿
    1.03
     disc
    1.01
     cds
    0.98
    Activations Density 0.211%

    No Known Activations