© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15064
    Prev
    Next
    INDEX
    Explanations

    terms related to economics and communication studies

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

    before punctuation or parenthesized tokens

    np_acts-logits-general · gemini-2.0-flash

    foreign language texts

    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
     дописавши
    -0.83
     pagrind
    -0.68
     seguinte
    -0.62
     atve
    -0.61
    ंदीखरीदारी
    -0.58
     acestui
    -0.57
    brokes
    -0.57
    crates
    -0.57
     entière
    -0.56
    AnimationsModule
    -0.55
    POSITIVE LOGITS
     specialising
    0.58
     specializing
    0.50
    OGND
    0.50
    ()]
    0.48
     województwie
    0.48
    Portail
    0.46
    出版年
    0.46
    境
    0.46
     nguoi
    0.45
    แบบ
    0.44
    Activations Density 0.066%

    No Known Activations