© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 7971
    Prev
    Next
    INDEX
    Explanations

    dialogue between characters

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

    Mathematical or foreign characters

    np_acts-logits-general · gemini-2.0-flash

    formal titles of address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    didSet
    -0.51
     suckers
    -0.51
    Weird
    -0.50
     cowardly
    -0.50
    Werde
    -0.49
     coward
    -0.49
    awsze
    -0.49
     sucker
    -0.49
     fave
    -0.48
     Weird
    -0.48
    POSITIVE LOGITS
     gentlemen
    0.81
     senhor
    0.73
     gentleman
    0.70
     sir
    0.70
     Mr
    0.68
     signore
    0.66
     please
    0.66
     monsieur
    0.65
    Mr
    0.64
    Sir
    0.63
    Activations Density 0.146%

    No Known Activations