© 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. 395
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and potential outcomes

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

    comparative statements expressing ease or similarity

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

    potential or possibility

    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
    contentLoaded
    -0.73
    StructEnd
    -0.73
    才会
    -0.63
    bootstrapcdn
    -0.62
    才有
    -0.61
    بوابة
    -0.57
    才可以
    -0.56
    才會
    -0.56
     Numerade
    -0.55
    才行
    -0.53
    POSITIVE LOGITS
     could
    1.00
     equally
    0.98
    could
    0.89
    Could
    0.78
     equivalently
    0.75
     Could
    0.74
     genauso
    0.71
     Equally
    0.69
     COULD
    0.68
     perfectamente
    0.64
    Activations Density 0.168%

    No Known Activations