© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K__L0-22
    6. 1090
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '.';
    -0.58
    sik
    -0.50
    InProgress
    -0.50
     tes
    -0.50
     '.')
    -0.49
     ""),
    -0.49
    ukar
    -0.49
     '.',
    -0.48
     tro
    -0.48
     él
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.90
    ValueGenerated
    0.90
    Hentet
    0.89
     CreateTagHelper
    0.86
    MockBean
    0.81
    ClientRect
    0.80
    Personensuche
    0.79
     NSCoder
    0.77
    berdayakan
    0.77
    الإنجليزية
    0.76
    Activations Density 0.050%

    No Known Activations