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. 5-GEMMASCOPE-RES-16K
    6. 3769
    Prev
    Next
    INDEX
    Explanations

    references to the LayoutInflater class in Android development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -1.08
     وتسجيلات
    -1.06
    enumi
    -1.04
     CreateTagHelper
    -1.02
     InputDecoration
    -1.02
     оригіналу
    -1.01
    tagHelperRunner
    -0.97
    AndEndTag
    -0.93
    出版年
    -0.92
     JpaRepository
    -0.88
    POSITIVE LOGITS
    LayoutInflater
    1.94
     LayoutInflater
    1.22
     FormControl
    0.67
    FormTagHelper
    0.67
    AnchorTagHelper
    0.62
    tpl
    0.60
    Controllers
    0.56
    SizedBox
    0.56
    beforeEach
    0.51
    ViewHolder
    0.50
    Activations Density 0.028%

    No Known Activations