© 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. 4196
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce lists or resources

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

    after "here are" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    lists of numbers

    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
     AssemblyCulture
    -0.75
    SequentialGroup
    -0.70
    Geplaatst
    -0.69
    Искәрмәләр
    -0.67
    存于互联网档案馆
    -0.65
     שוליים
    -0.63
     صوتيه
    -0.61
     CreateTagHelper
    -0.61
    setVerticalGroup
    -0.58
     Roskov
    -0.56
    POSITIVE LOGITS
     five
    1.25
     Top
    1.17
    Top
    1.09
     seven
    1.07
     top
    1.02
     six
    0.99
     ten
    0.99
     Five
    0.98
     cinco
    0.98
    five
    0.97
    Activations Density 0.116%

    No Known Activations