© 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. 24-GEMMASCOPE-RES-16K
    6. 12355
    Prev
    Next
    INDEX
    Explanations

    elements related to charts and diagrams

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

    presentations and diagrams

    np_acts-logits-general · gemini-2.0-flash

    visual aids and diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WebDriverWait
    -0.66
    Portály
    -0.64
     resourceCulture
    -0.61
    forName
    -0.60
    DllImport
    -0.58
     cherchés
    -0.57
    principalTable
    -0.56
    matchCondition
    -0.54
    TextWatcher
    -0.54
     getItemId
    -0.54
    POSITIVE LOGITS
     slides
    1.46
     presentation
    1.41
     charts
    1.40
     slide
    1.35
     PowerPoint
    1.33
     diagrams
    1.31
     presentations
    1.29
     diagram
    1.26
     chart
    1.26
     Presentation
    1.25
    Activations Density 0.479%

    No Known Activations