© 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. 4-GEMMASCOPE-RES-16K
    6. 3864
    Prev
    Next
    INDEX
    Explanations

    keywords related to scalability and efficiency in algorithms and designs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StringField
    -0.65
     nakalista
    -0.60
     GetEnumerator
    -0.59
    SerializedName
    -0.56
    '])){
    
    -0.55
    urfacing
    -0.55
    blica
    -0.53
    setupUi
    -0.53
     Verbal
    -0.52
     نص
    -0.52
    POSITIVE LOGITS
     robustness
    1.17
     resilient
    1.05
     robust
    1.05
    robust
    0.96
    Robust
    0.95
     Robust
    0.95
     adaptable
    0.95
     flexibility
    0.91
     resilience
    0.90
     flexible
    0.90
    Activations Density 1.090%

    No Known Activations