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. 2-GEMMASCOPE-RES-16K
    6. 6337
    Prev
    Next
    INDEX
    Explanations

    specific formats related to structured or organized lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ranton
    -0.94
    ScopeManager
    -0.89
    mybatisplus
    -0.79
     تضيفلها
    -0.74
    />
    
    -0.72
     "..\..\
    -0.72
    انيف
    -0.72
     propOrder
    -0.71
    商品説明
    -0.71
    '));
    
    -0.69
    POSITIVE LOGITS
    RectangleBorder
    0.80
     useRouter
    0.72
    wpdb
    0.60
    viewDidLoad
    0.52
    NavController
    0.51
    OptionsMenu
    0.50
    elance
    0.48
     réunis
    0.48
    __':
    0.48
    ContentAsync
    0.47
    Activations Density 0.247%

    No Known Activations