© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 2926
    Prev
    Next
    INDEX
    Explanations

    details related to font and text styling properties in programming contexts

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

    specifications related to font and text styling properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.54
     Thomas
    -0.44
     pasillo
    -0.42
     absolutely
    -0.41
     totally
    -0.41
    南北
    -0.40
     вовсе
    -0.40
     ireo
    -0.40
     Colomb
    -0.40
    cences
    -0.39
    POSITIVE LOGITS
     fontSize
    1.02
    fontSize
    0.99
    FontOfSize
    0.99
     fontsize
    0.87
     size
    0.84
    TextSize
    0.79
    FontSize
    0.78
    tvguidetime
    0.78
    fontsize
    0.78
    /*
    0.78
    Activations Density 0.055%

    No Known Activations