© 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. 7810
    Prev
    Next
    INDEX
    Explanations

    conjunctions and words indicating connections or additions between ideas

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

    Tokens after "and" or "or"

    np_acts-logits-general · gemini-2.0-flash

    connecting items or groups

    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
     تضيفلها
    -1.17
     disambiguazione
    -1.16
    новниш
    -1.07
    adaptiveStyles
    -1.00
     '\\;'
    -0.99
     Roskov
    -0.99
     myſelf
    -0.97
    ValueStyle
    -0.97
    AndEndTag
    -0.93
     Efq
    -0.93
    POSITIVE LOGITS
     system
    0.75
     second
    0.73
     two
    0.71
     list
    0.70
     portion
    0.70
     website
    0.70
     final
    0.69
     program
    0.69
     series
    0.69
     piece
    0.69
    Activations Density 0.411%

    No Known Activations