© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15286
    Prev
    Next
    INDEX
    Explanations

    mentions of economic or social disparities, specifically focusing on the concept of "gaps"

    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
    cplusplus
    -0.56
     contraseña
    -0.45
    loadImage
    -0.45
    abbaye
    -0.43
    loadAll
    -0.41
    épreuve
    -0.41
     bilen
    -0.40
     ingresso
    -0.39
     bukti
    -0.39
     szabad
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    1.19
     gap
    0.98
    الإنجليزية
    0.94
    Personendaten
    0.88
     gaps
    0.88
     Gaps
    0.86
     Gap
    0.84
    gap
    0.81
    Gap
    0.79
    })();
    0.78
    Activations Density 1.698%

    No Known Activations