Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13135
    Prev
    Next
    INDEX
    Explanations

    sections of text containing the beginning of data or document structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exacts
    -0.63
    prelude
    -0.63
     WebDriverWait
    -0.61
     pymongo
    -0.60
     aDecoder
    -0.59
     onAnimation
    -0.59
    WindowConstants
    -0.59
     tkinter
    -0.58
     DBNull
    -0.58
    BindingResult
    -0.57
    POSITIVE LOGITS
    filepath
    1.43
     filepath
    0.91
     متعلقه
    0.77
     للمعارف
    0.76
     ujednoznacz
    0.69
    chossen
    0.64
     للاسماء
    0.62
    tvguidetime
    0.62
     الحره
    0.57
    $}}
    0.56
    Activations Density 0.022%

    No Known Activations