© 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. 25-GEMMASCOPE-RES-16K
    11. 4473
    Prev
    Next
    INDEX
    Explanations

    actions related to managing tasks and data structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.56
    ScopeManager
    -0.56
     وتسجيلات
    -0.55
     doInBackground
    -0.54
    tagHelperRunner
    -0.52
     ویکی‌پدی
    -0.44
    Хьажоргаш
    -0.43
    itaj
    -0.43
    PMS
    -0.43
     архивлан
    -0.42
    POSITIVE LOGITS
     recentemente
    0.60
    utnik
    0.59
    NOPQRST
    0.55
    WebVitals
    0.54
     JMenuItem
    0.53
    XmlEnum
    0.52
    حياته
    0.52
    fjspx
    0.52
     configureStore
    0.52
     propOrder
    0.51
    Activations Density 0.097%

    No Known Activations