© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10623
    Prev
    Next
    INDEX
    Explanations

    elements related to crafting and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    DIY creations, crafts, and projects

    np_acts-logits-general · gemini-2.0-flash

    making crafts and projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.59
    водства
    -0.52
    XmlAccessType
    -0.52
     initComponents
    -0.51
    مؤ
    -0.50
     territorios
    -0.50
    multer
    -0.49
     unggul
    -0.49
     obligator
    -0.49
     emiti
    -0.47
    POSITIVE LOGITS
     creations
    1.04
     creation
    0.91
     DIY
    0.88
     masterpiece
    0.85
     masterpieces
    0.81
     diy
    0.80
     projects
    0.80
     custom
    0.79
     homemade
    0.78
     créations
    0.74
    Activations Density 0.252%

    No Known Activations