© 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. 4-GEMMASCOPE-RES-16K
    11. 10368
    Prev
    Next
    INDEX
    Explanations

    different types of quotation marks and apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.75
    bibfield
    -0.72
    ItemBackground
    -0.71
    BibitemShut
    -0.68
     Vikipedi
    -0.68
     الحره
    -0.65
    therosclerosis
    -0.62
     fumar
    -0.62
     protoimpl
    -0.60
    obenz
    -0.59
    POSITIVE LOGITS
    Xna
    0.57
    LikeLike
    0.52
    XSSF
    0.50
    /
    0.49
    providedIn
    0.47
     sendiri
    0.46
     sectores
    0.45
    -
    0.45
     '\\;'
    0.45
     selve
    0.43
    Activations Density 0.416%

    No Known Activations