© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14684
    Prev
    Next
    INDEX
    Explanations

    keywords related to historical context and significance

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

    Follows titles, headings or sentence starts

    np_acts-logits-general · gemini-2.0-flash

    movements and traditions

    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
    AddTagHelper
    -0.83
     مشين
    -0.68
    esModule
    -0.65
     AssemblyTitle
    -0.64
    NameInMap
    -0.64
     humana
    -0.59
    HasIndex
    -0.59
    matchCondition
    -0.59
    +#+#
    -0.57
    adaptiveStyles
    -0.57
    POSITIVE LOGITS
     movement
    1.00
    movement
    0.88
     tradition
    0.86
     trends
    0.85
     traditions
    0.85
     movements
    0.85
     courant
    0.84
     schools
    0.82
    schools
    0.80
     Movement
    0.79
    Activations Density 0.311%

    No Known Activations