© 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. 12312
    Prev
    Next
    INDEX
    Explanations

    action-packed sequences and high-intensity moments in films

    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
    AddTagHelper
    -0.62
     createState
    -0.60
    endpush
    -0.57
     étoit
    -0.54
    tvguidetime
    -0.54
    KommentareTeilen
    -0.52
    EDEFAULT
    -0.52
    NameLabel
    -0.51
    GenerationType
    -0.51
    internalType
    -0.51
    POSITIVE LOGITS
     scenes
    1.82
     scene
    1.71
     Scenes
    1.46
    scenes
    1.36
    Scenes
    1.35
    scene
    1.34
     sequences
    1.33
     scènes
    1.32
     Scene
    1.31
     scena
    1.29
    Activations Density 0.215%

    No Known Activations