© 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. 1361
    Prev
    Next
    INDEX
    Explanations

    features and characteristics of luxurious properties

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

    phrases related to luxury features in properties

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

    features of a house

    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
    ReusableCell
    -0.71
    GEBURTSDATUM
    -0.58
    脚注の使い方
    -0.51
    ărul
    -0.51
     незавершена
    -0.50
    sidemargin
    -0.49
    DockStyle
    -0.49
    tagHelperRunner
    -0.48
     Grüsse
    -0.48
    linearGradient
    -0.48
    POSITIVE LOGITS
     Fully
    0.71
     fitted
    0.66
     Fitted
    0.65
     fully
    0.61
     Massive
    0.61
    fitted
    0.61
    Fully
    0.61
     Semi
    0.60
     Leading
    0.59
    Fitted
    0.58
    Activations Density 0.005%

    No Known Activations