© 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. 2-GEMMASCOPE-RES-16K
    11. 3216
    Prev
    Next
    INDEX
    Explanations

    negations and auxiliary verbs associated with uncertainty or inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.63
     CommonModule
    -0.45
     tient
    -0.44
    tomatik
    -0.44
    PhysRev
    -0.43
     Kaplan
    -0.42
     mapStateToProps
    -0.42
    wege
    -0.42
    вость
    -0.42
     numeri
    -0.42
    POSITIVE LOGITS
     Roskov
    0.77
    doria
    0.66
    Hochspringen
    0.63
     esternos
    0.61
     intptr
    0.60
    ngrx
    0.57
    ThemeOverlay
    0.56
    enoord
    0.56
     propOrder
    0.55
     елның
    0.54
    Activations Density 0.494%

    No Known Activations