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. 4-GEMMASCOPE-RES-16K
    6. 15906
    Prev
    Next
    INDEX
    Explanations

    references to API structures and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.70
     SwiftUI
    -0.69
     createSprite
    -0.68
    脚注の使い方
    -0.68
     InputDecoration
    -0.67
    GeneratedValue
    -0.65
    حياته
    -0.65
     onCreateView
    -0.65
     bVar
    -0.64
    scriptcase
    -0.64
    POSITIVE LOGITS
     API
    2.74
    API
    2.36
     APIs
    2.34
     api
    2.29
     Api
    2.20
    Api
    2.11
    api
    2.06
    APIs
    1.92
    APIS
    1.52
     ApiService
    1.33
    Activations Density 0.041%

    No Known Activations