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. 10-GEMMASCOPE-RES-16K
    6. 12669
    Prev
    Next
    INDEX
    Explanations

    attributes and methods related to object-oriented programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.62
    adaptiveStyles
    -0.60
    BeginInit
    -0.59
    Cyfeiriadau
    -0.57
    IUrlHelper
    -0.57
    Jereo
    -0.53
    <bos>
    -0.53
    లాలు
    -0.52
     Exactos
    -0.52
    --){
    -0.50
    POSITIVE LOGITS
     Normdatei
    0.63
     viewDidLoad
    0.58
    mybatisplus
    0.54
    ButterKnife
    0.53
    prisma
    0.52
     skimage
    0.50
    opardy
    0.50
     financeira
    0.50
    SPJ
    0.50
    multer
    0.49
    Activations Density 0.058%

    No Known Activations