© 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. 12720
    Prev
    Next
    INDEX
    Explanations

    mechanical components related to machining tools

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

    CNC, machining, or milling context

    np_acts-logits-general · gemini-2.0-flash

    machining tools and processes

    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
    ุง
    -0.52
     Stret
    -0.47
     Stre
    -0.46
    лактика
    -0.45
    กรณ์
    -0.45
     BoxDecoration
    -0.45
    hyo
    -0.45
     kiện
    -0.44
     Molo
    -0.43
    Textarea
    -0.43
    POSITIVE LOGITS
     CNC
    0.98
     Milling
    0.97
     milling
    0.96
    CNC
    0.93
     cnc
    0.92
     cutting
    0.88
    cutting
    0.88
     router
    0.87
     machining
    0.87
     drill
    0.86
    Activations Density 0.272%

    No Known Activations