Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15296
    Prev
    Next
    INDEX
    Explanations

    sentences discussing the functionality and features of email applications

    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
     ExecuteAsync
    -0.67
    AddTagHelper
    -0.63
    JspWriter
    -0.62
    createCanvas
    -0.62
    SourceChecksum
    -0.61
    BeginContext
    -0.61
    تقاوى
    -0.61
    WebElementEntity
    -0.59
     MaterialApp
    -0.59
    IndentedString
    -0.58
    POSITIVE LOGITS
     sync
    0.88
     syncing
    0.86
     Sync
    0.82
     contacts
    0.82
     Contacts
    0.81
     synchronization
    0.80
    Sync
    0.80
     synced
    0.79
     organizer
    0.78
     sincron
    0.78
    Activations Density 0.350%

    No Known Activations