© 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. 10-GEMMASCOPE-RES-16K
    6. 6257
    Prev
    Next
    INDEX
    Explanations

    elements related to chart and graph properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementGuid
    -1.09
    RenderAtEndOf
    -0.78
     GenerationType
    -0.77
    tagHelperRunner
    -0.75
    antMatchers
    -0.75
    HomeAsUpEnabled
    -0.74
    ScopeManager
    -0.74
    RectangleBorder
    -0.73
    PreExecute
    -0.73
    InjectAttribute
    -0.73
    POSITIVE LOGITS
     priests
    0.52
    jfree
    0.52
     charts
    0.49
     trellis
    0.48
     download
    0.45
     visualizations
    0.44
     graphs
    0.44
     presentation
    0.43
     plotly
    0.43
    ereich
    0.42
    Activations Density 0.202%

    No Known Activations