© 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. 11-GEMMASCOPE-RES-16K
    6. 1453
    Prev
    Next
    INDEX
    Explanations

    technical terms and code snippets related to programming, specifically Java imports and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -1.20
    Personendaten
    -1.15
    хьтан
    -1.15
     kaarangay
    -1.11
    <bos>
    -1.10
    expandindo
    -1.10
     Meksiku
    -1.07
    Vidite
    -1.07
    InjectAttribute
    -1.04
    تقاوى
    -1.02
    POSITIVE LOGITS
     aren
    0.48
     isn
    0.44
    Wasn
    0.44
     don
    0.41
    0.40
    ̩
    0.39
    그는
    0.38
    [
    
    0.36
    queiro
    0.36
    unción
    0.34
    Activations Density 0.525%

    No Known Activations