© 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. 435
    Prev
    Next
    INDEX
    Explanations

    complex discussions about race and cultural identity

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

    statements about gameplay experiences

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

    questioning and speculative phrases

    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
     fabulous
    -0.61
    Whew
    -0.57
    !
    -0.55
     terrific
    -0.52
     lovely
    -0.51
     wonderful
    -0.51
    とっても
    -0.50
    fabulous
    -0.49
    なかなか
    -0.48
    !).
    -0.47
    POSITIVE LOGITS
    /=
    0.92
     objectively
    0.91
     Lmao
    0.81
     lmao
    0.78
     subjective
    0.76
     argumento
    0.75
     idk
    0.74
     Idk
    0.74
    Referències
    0.73
    Idk
    0.73
    Activations Density 0.134%

    No Known Activations