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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4523
    Prev
    Next
    INDEX
    Explanations

    references to the concept of a "home" or "dashboard" in a user interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.39
    ❹
    -0.34
     judiciales
    -0.30
     Comentarios
    -0.28
     числе
    -0.28
    fileupload
    -0.28
    锈钢
    -0.28
     Jeremiah
    -0.27
     transacción
    -0.27
     perfección
    -0.27
    POSITIVE LOGITS
     Home
    1.10
    Home
    1.06
     HomeScreen
    1.01
     home
    1.01
     HOME
    0.98
     homepage
    0.94
     HomeController
    0.94
    home
    0.94
    Homepage
    0.93
     HomePage
    0.93
    Activations Density 0.159%

    No Known Activations