© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1330
    Prev
    Next
    INDEX
    Explanations

    specific document formatting markers or structures

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

    brackets and specific types of formatting indicators

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

    Introduction

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     berät
    -0.57
    UnsafeEnabled
    -0.56
     grazia
    -0.54
     članak
    -0.52
     soulign
    -0.52
     exceptionnel
    -0.51
    nantes
    -0.51
    ceğine
    -0.51
     felé
    -0.51
    戬
    -0.51
    POSITIVE LOGITS
     nakalista
    0.63
     الحره
    0.61
    findpost
    0.60
    src
    0.59
    TagMode
    0.57
     Infórmanos
    0.57
     تضيفلها
    0.55
    
    0.52
     globular
    0.52
    pdf
    0.52
    Activations Density 0.022%

    No Known Activations