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. MLP Out - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8896
    Prev
    Next
    INDEX
    Explanations

    references to different modules in a technical or software context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     module
    -2.64
     Module
    -2.36
    module
    -2.33
    Module
    -2.23
     modules
    -2.17
     Modules
    -1.97
     módulo
    -1.83
     MODULE
    -1.73
    modules
    -1.69
    模块
    -1.60
    POSITIVE LOGITS
    MockMvc
    0.71
    multer
    0.64
     MonoBehaviour
    0.62
    MessageTagHelper
    0.59
    XmlAccessType
    0.58
     soup
    0.58
    makeConstraints
    0.56
    principalTable
    0.56
    icitis
    0.56
    stination
    0.55
    Activations Density 0.138%

    No Known Activations