© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 9228
    Prev
    Next
    INDEX
    Explanations

    mentions of significant personal achievements and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -1.05
     المعيارى
    -0.96
     GenerationType
    -0.90
     FetchType
    -0.84
    ItemBackground
    -0.82
     estekak
    -0.81
    AndroidJUnit
    -0.80
    Personensuche
    -0.80
    رشف
    -0.78
     propOrder
    -0.76
    POSITIVE LOGITS
     collaborated
    0.50
     projects
    0.48
     co
    0.47
    bitkan
    0.45
    感兴趣
    0.45
     Distinction
    0.45
    named
    0.45
     published
    0.45
    อนไลน์
    0.45
     blog
    0.43
    Activations Density 0.269%

    No Known Activations