© 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-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 16019
    Prev
    Next
    INDEX
    Explanations

    references to MVC (Model-View-Controller) framework concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sä
    -0.46
     désolés
    -0.39
    おり
    -0.38
     case
    -0.38
    yttää
    -0.37
    sedur
    -0.36
    难题
    -0.36
     umat
    -0.35
    wps
    -0.35
     race
    -0.35
    POSITIVE LOGITS
     AssemblyTitle
    0.85
    StoryboardSegue
    0.83
    ViewFeatures
    0.79
    ReusableCell
    0.66
     nahilalakip
    0.66
     initComponents
    0.65
    UrlResolution
    0.65
     EconPapers
    0.64
     IBOutlet
    0.63
    bootstrapcdn
    0.60
    Activations Density 0.031%

    No Known Activations