© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11678
    Prev
    Next
    INDEX
    Explanations

    elements and components related to user interfaces in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code and UI elements related to "View"

    np_acts-logits-general · gemini-2.0-flash

    UI programming views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.93
     CreateTagHelper
    -0.78
     propOrder
    -0.76
     وتسجيلات
    -0.68
    +#+#
    -0.68
    httphttps
    -0.65
    tagHelperRunner
    -0.62
     betweenstory
    -0.59
    JspWriter
    -0.57
    +:+
    -0.55
    POSITIVE LOGITS
     views
    0.68
     view
    0.66
     viewDidLoad
    0.65
     Views
    0.62
    pager
    0.60
    getView
    0.58
    aarrggbb
    0.57
    PAGER
    0.57
     View
    0.56
    ropra
    0.53
    Activations Density 0.085%

    No Known Activations