© 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. 1-GEMMASCOPE-RES-16K
    11. 14683
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes, indicating a focus on markup elements and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.44
    NameInMap
    -1.21
    SuccessListener
    -1.02
     createState
    -1.02
     getItemId
    -0.99
     StatefulWidget
    -0.98
     eventdata
    -0.97
    SourceChecksum
    -0.95
     الرياضيه
    -0.94
    IActionResult
    -0.94
    POSITIVE LOGITS
    trap
    0.38
    setLine
    0.38
     rounded
    0.37
     kics
    0.36
     superfí
    0.36
     i
    0.35
     précédents
    0.35
     précédent
    0.35
    勢
    0.34
    ومه
    0.33
    Activations Density 0.459%

    No Known Activations