© 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. 34
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures or programming constructs

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

    Appears after special characters or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    acronyms and specific technical terms

    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
    .
    -0.78
    <eos>
    -0.75
    ,
    -0.71
    ↵↵
    -0.70
    ;
    -0.69
    :
    -0.67
    !
    -0.64
    ?
    -0.64
    ),
    -0.63
    ↵
    -0.63
    POSITIVE LOGITS
     itſelf
    1.21
    PreferredItem
    1.17
     myſelf
    1.16
     Efq
    1.14
     يتيمه
    1.14
     Jefus
    1.13
     الرياضيه
    1.11
     Мексичка
    1.07
     disambiguazione
    1.06
    AsUp
    1.06
    Activations Density 0.725%

    No Known Activations