© 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. 21-GEMMASCOPE-RES-16K
    11. 2482
    Prev
    Next
    INDEX
    Explanations

    elements and attributes in HTML forms, particularly inputs, text areas, and related HTML attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.65
     Meksiku
    -0.46
    ardo
    -0.45
     Dar
    -0.44
     arch
    -0.44
    Scalars
    -0.44
     eig
    -0.43
    Bibliograf
    -0.43
     porte
    -0.43
    nyder
    -0.42
    POSITIVE LOGITS
     required
    0.82
     placeholder
    0.81
    required
    0.80
    placeholder
    0.72
     Required
    0.70
     Placeholder
    0.69
     requerida
    0.69
     requerido
    0.67
    Required
    0.67
    __(/*!
    0.65
    Activations Density 0.049%

    No Known Activations