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. 5229
    Prev
    Next
    INDEX
    Explanations

    Java annotations and their associated classes used in object-relational mapping (ORM)

    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
     StatefulWidget
    -0.81
     BorderRadius
    -0.75
     &___
    -0.68
     Commencez
    -0.65
     препратки
    -0.64
    iega
    -0.64
     splin
    -0.61
     ligiloj
    -0.60
     للمعارف
    -0.60
     ReactDOM
    -0.60
    POSITIVE LOGITS
    IsContent
    0.52
    ComponentScan
    0.48
     CreateTagHelper
    0.48
     chrétiens
    0.47
     olmayan
    0.46
    ̸
    0.45
     saan
    0.44
    JsonProperty
    0.42
     Grecs
    0.42
    anen
    0.41
    Activations Density 0.077%

    No Known Activations