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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10669
    Prev
    Next
    INDEX
    Explanations

    references to user interface (UI) elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ![
    -0.62
    haft
    -0.62
    ajuato
    -0.60
    NavController
    -0.59
    mogorov
    -0.57
     bArr
    -0.56
    новниш
    -0.56
    etragen
    -0.56
    dal
    -0.55
     Jérusalem
    -0.55
    POSITIVE LOGITS
     ui
    0.93
     Interfaces
    0.90
     interfaces
    0.87
     widgets
    0.78
     интерфей
    0.77
     Interface
    0.76
     INTERFACE
    0.76
     interface
    0.75
    Kui
    0.73
     Widgets
    0.72
    Activations Density 0.085%

    No Known Activations