© 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 EvalsExportsinterp-engineNEWAPI 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. 4213
    Prev
    Next
    INDEX
    Explanations

    attributes related to accessibility and roles in web elements

    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
     Ocean
    -0.60
    stdlib
    -0.60
     Atlántico
    -0.59
     Sanz
    -0.57
     Saunders
    -0.56
    ن
    -0.56
     frot
    -0.56
     Marino
    -0.54
     karşılaş
    -0.54
    richTextPanel
    -0.54
    POSITIVE LOGITS
     aria
    1.35
     ARIA
    1.22
     Aria
    1.12
    Aria
    1.04
     Uniti
    0.93
    styleType
    0.92
     CURLOPT
    0.89
    ARIA
    0.86
     وتسجيلات
    0.83
     оригіналу
    0.82
    Activations Density 0.020%

    No Known Activations