© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5937
    Prev
    Next
    INDEX
    Explanations

    the symbol "varepsilon" or its variations, which typically denote a small positive number in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.52
     sahip
    -0.49
    hyd
    -0.48
     lampada
    -0.47
    ManagedBean
    -0.46
     sahiptir
    -0.46
     Kohlen
    -0.46
     legno
    -0.45
     Hyman
    -0.44
    +#+#
    -0.44
    POSITIVE LOGITS
    epsilon
    2.44
    varepsilon
    2.42
     epsilon
    2.05
     ε
    1.95
    ε
    1.76
    ϵ
    1.73
    Epsilon
    1.55
     Epsilon
    1.43
     ɛ
    1.34
    
    1.30
    Activations Density 0.208%

    No Known Activations