© 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. 3295
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal and corporate structures

    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
    Morfologia
    -0.66
     église
    -0.59
     kaarangay
    -0.58
     OMITBAD
    -0.58
     orgasm
    -0.57
     nakalista
    -0.57
    lafen
    -0.56
     econômica
    -0.54
    IContainer
    -0.54
     impossível
    -0.53
    POSITIVE LOGITS
     or
    0.69
    verwijspagina
    0.64
     often
    0.63
     such
    0.62
    racha
    0.54
     لينك
    0.54
    んだり
    0.54
     bijvoorbeeld
    0.53
     integr
    0.53
    例句
    0.53
    Activations Density 0.528%

    No Known Activations