© 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. 19-GEMMASCOPE-RES-16K
    11. 12090
    Prev
    Next
    INDEX
    Explanations

    references to actions and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.71
     GenerationType
    -0.70
     дописавши
    -0.68
    GEBURTSDATUM
    -0.58
     ostavi
    -0.57
    IonicModule
    -0.57
     Owls
    -0.57
    الدراسه
    -0.56
     useAppContext
    -0.56
    WriteTagHelper
    -0.55
    POSITIVE LOGITS
    ToAction
    0.88
    getAction
    0.84
     ACTION
    0.84
     Action
    0.82
     Actions
    0.81
     actions
    0.80
    ACTION
    0.78
     action
    0.78
    actions
    0.78
    Actions
    0.76
    Activations Density 0.122%

    No Known Activations