© 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. 15-GEMMASCOPE-RES-16K
    11. 13151
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with hypotheses and demands in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    رشف
    -0.72
    حياتها
    -0.71
    Brainz
    -0.67
     BoxDecoration
    -0.67
    bootstrapcdn
    -0.67
    mergeFrom
    -0.67
     estekak
    -0.65
     للمعارف
    -0.65
    Autoritní
    -0.63
    OGND
    -0.62
    POSITIVE LOGITS
     conjecture
    0.63
     noted
    0.61
     eluc
    0.56
     señ
    0.55
     XCTest
    0.55
     sugger
    0.54
     '.')
    0.54
     elucid
    0.53
     sugg
    0.53
     remark
    0.52
    Activations Density 0.157%

    No Known Activations