© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 436
    Prev
    Next
    INDEX
    Explanations

    instructions related to health and safety precautions

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

    instructions and guidelines related to safety and health measures

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

    advice and instructions

    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
     due
    -0.83
     whereas
    -0.76
    whereas
    -0.75
    due
    -0.75
     debido
    -0.75
     Due
    -0.72
    AddTagHelper
    -0.68
    Whereas
    -0.67
    Due
    -0.66
     Whereas
    -0.66
    POSITIVE LOGITS
     preferably
    1.14
    preferably
    1.08
     yourself
    0.95
     Preferably
    0.91
     gärna
    0.83
     jangan
    0.82
     ideally
    0.76
     préférence
    0.76
     nhé
    0.76
     Jangan
    0.71
    Activations Density 0.174%

    No Known Activations