© 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. 21-GEMMASCOPE-RES-16K
    6. 14921
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details related to watch mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.68
    WebServlet
    -0.57
    Manbalar
    -0.52
    ьаж
    -0.51
     kaynağından
    -0.51
     doInBackground
    -0.51
    rawDesc
    -0.51
    ImageContext
    -0.50
     cytos
    -0.49
     JpaRepository
    -0.48
    POSITIVE LOGITS
     watch
    2.07
     watches
    1.95
    watch
    1.75
     Watch
    1.73
    watches
    1.65
    Watch
    1.60
     Watches
    1.60
     WATCH
    1.51
     wrist
    1.39
    WATCH
    1.32
    Activations Density 0.070%

    No Known Activations