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. 12347
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and references related to biological processes and gene analysis

    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
     reuniones
    -0.51
    ധ
    -0.50
    Petra
    -0.48
     riusc
    -0.47
     ricord
    -0.46
     trhu
    -0.44
     hated
    -0.44
     rojos
    -0.44
     seduta
    -0.43
    Outdoor
    -0.43
    POSITIVE LOGITS
     propOrder
    0.91
     CreateTagHelper
    0.76
     Roskov
    0.74
    richTextPanel
    0.73
    addCriterion
    0.72
     revisor
    0.70
    MessageOf
    0.70
     Genomics
    0.70
     lenker
    0.68
    Diweddarwch
    0.68
    Activations Density 3.154%

    No Known Activations