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. 11099
    Prev
    Next
    INDEX
    Explanations

    references to essential or crucial components and concepts

    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
    WRP
    -0.90
    COUVER
    -0.89
    Hozzáférés
    -0.89
    stackoverflow
    -0.85
    ChromeDriver
    -0.85
    GroupLayout
    -0.84
    ScopeManager
    -0.84
    piram
    -0.83
    ollectionView
    -0.81
    netbeans
    -0.81
    POSITIVE LOGITS
     essential
    2.54
    essential
    2.40
     Essential
    2.28
    Essential
    2.23
     esenciales
    1.93
     essentials
    1.79
     essenziale
    1.78
     essentiel
    1.77
     essentiels
    1.74
     essenciais
    1.69
    Activations Density 0.085%

    No Known Activations