© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15212
    Prev
    Next
    INDEX
    Explanations

    phrases related to overcoming difficulties and taking action

    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
     totul
    -0.58
     addirittura
    -0.57
     incluso
    -0.56
     appunto
    -0.55
     seguramente
    -0.55
     pourrez
    -0.54
    perhaps
    -0.53
    なんと
    -0.52
     necessárias
    -0.51
     måske
    -0.51
    POSITIVE LOGITS
     للمعارف
    1.06
    findpost
    0.95
     дописавши
    0.91
    DeleteBehavior
    0.91
     BoxDecoration
    0.90
     defaultstate
    0.85
     HasFactory
    0.83
     الحره
    0.83
     AssemblyCompany
    0.82
    GEBURTSDATUM
    0.81
    Activations Density 1.283%

    No Known Activations