Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10841
    Prev
    Next
    INDEX
    Explanations

    elements related to code structures and configurations

    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
     Infórmanos
    -0.73
    tagHelperRunner
    -0.63
     décédé
    -0.56
     NSCoder
    -0.56
     Seeder
    -0.55
     døde
    -0.55
     zmar
    -0.55
     élu
    -0.55
    fromnode
    -0.54
     esimer
    -0.54
    POSITIVE LOGITS
    DataAnnotations
    0.74
    putExtra
    0.65
    AddHtmlAttribute
    0.61
    :✨
    0.59
    CURLOPT
    0.55
    openqa
    0.54
    curo
    0.53
    /*---
    0.52
     include
    0.52
    اكم
    0.52
    Activations Density 0.240%

    No Known Activations