© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9067
    Prev
    Next
    INDEX
    Explanations

    references to various medical terminologies and acronyms

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

    Tokens containing "ae" or "æ"

    np_acts-logits-general · gemini-2.0-flash

    ae or æ tokens

    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
    cahontas
    -0.52
    RegressionTest
    -0.51
     imp
    -0.50
    ragamo
    -0.50
     pí
    -0.50
    dientemente
    -0.49
     listView
    -0.48
    illoma
    -0.48
     Trinity
    -0.48
     hopp
    -0.47
    POSITIVE LOGITS
     Nae
    0.85
     Kae
    0.84
     Ae
    0.81
     שוליים
    0.79
     Hae
    0.78
     Reſ
    0.75
     Aether
    0.74
     ae
    0.74
     Administrativna
    0.73
     AER
    0.69
    Activations Density 0.163%

    No Known Activations