© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7665
    Prev
    Next
    INDEX
    Explanations

    instances of the word "use" and its variations in relation to application and implementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gwend
    -0.77
     autorytatywna
    -0.76
     ProductService
    -0.73
     iParam
    -0.72
    AnimationsModule
    -0.71
    quium
    -0.71
    reportWebVitals
    -0.70
    WriteTagHelper
    -0.70
     lexer
    -0.69
     MenuView
    -0.69
    POSITIVE LOGITS
     uses
    1.45
     Use
    1.45
     use
    1.40
     Uses
    1.39
     Using
    1.38
    Use
    1.37
    Using
    1.32
     USING
    1.32
     using
    1.28
    Uses
    1.28
    Activations Density 0.347%

    No Known Activations