© 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. 20-GEMMASCOPE-RES-16K
    11. 15769
    Prev
    Next
    INDEX
    Explanations

    elements related to figures and graphical representations in documents

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

    "textwidth" token in LaTeX-like image inclusions

    np_acts-logits-general · gemini-2.0-flash

    document width and image inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]))
    -0.81
    ⓧ
    -0.81
    ])))
    -0.78
    ']);
    -0.69
    }))
    -0.69
    ]),
    -0.69
    '])->
    -0.68
    '],
    -0.67
    '])
    -0.67
    ("")]
    -0.67
    POSITIVE LOGITS
    ){
    0.70
    édrale
    0.64
    }{
    0.55
    ]{
    0.55
    rangea
    0.54
     Motta
    0.54
    textwidth
    0.53
     BorderSide
    0.52
    tagext
    0.51
    verwijspagina
    0.51
    Activations Density 0.147%

    No Known Activations