© 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. 430
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or dependency in contexts involving help or support

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

    statements expressing ability or potential outcomes related to a program

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

    would not exist without

    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
    ToLeft
    -0.63
    Demografía
    -0.60
     שוליים
    -0.56
    πάν
    -0.48
    //*[@
    -0.46
     myſelf
    -0.45
    XMLSchema
    -0.44
     ujednoznacz
    -0.43
    ặn
    -0.43
    хьтан
    -0.43
    POSITIVE LOGITS
     wouldn
    0.76
     Without
    0.76
     without
    0.73
    Ohne
    0.73
     Ohne
    0.73
    Without
    0.72
     incomplete
    0.72
     Без
    0.68
    without
    0.67
     ohne
    0.66
    Activations Density 0.051%

    No Known Activations