© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3434
    Prev
    Next
    INDEX
    Explanations

    notifications and updates related to meeting recordings and file uploads

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

    prompts, popups, or notifications

    np_acts-logits-general · gemini-2.0-flash

    messages and screens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.55
    __(/*!
    -0.54
    LookAnd
    -0.48
    ValueStyle
    -0.48
    InputTagHelper
    -0.47
     GenerationType
    -0.44
     ویکی‌پدیا
    -0.44
    rrggbb
    -0.43
    UnsafeEnabled
    -0.43
    tagHelperRunner
    -0.42
    POSITIVE LOGITS
     screen
    0.61
     prompting
    0.55
     prompt
    0.54
     automatically
    0.53
    écran
    0.52
     Meldung
    0.51
     automatiquement
    0.50
     schermata
    0.50
    screen
    0.50
     greeted
    0.50
    Activations Density 0.362%

    No Known Activations