© 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. 20-GEMMASCOPE-RES-16K
    11. 3970
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to algebraic structures and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after "can", "may", or "we"

    np_acts-logits-general · gemini-2.0-flash

    we can verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secco
    -0.53
    Heter
    -0.49
    araus
    -0.49
     przys
    -0.48
     Relationship
    -0.47
    subequations
    -0.46
    衍
    -0.46
    CrossRef
    -0.46
    cetto
    -0.46
     Concepts
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.91
     betweenstory
    0.89
    省市镇
    0.76
     gyhoeddwyd
    0.74
    ViewFeatures
    0.72
     يتيمه
    0.71
    
    0.70
     Walkover
    0.70
    rawDesc
    0.70
     مشين
    0.69
    Activations Density 3.853%

    No Known Activations