© 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. 11-GEMMASCOPE-RES-16K
    11. 1648
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control flow structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    subsubsection
    -0.65
     تانيه
    -0.65
    XmlType
    -0.63
     Reiche
    -0.63
    audiovisuel
    -0.61
    DrawerToggle
    -0.59
     BoxDecoration
    -0.58
     brood
    -0.58
     HAP
    -0.57
    блиоте
    -0.57
    POSITIVE LOGITS
    Искәрмәләр
    0.95
    ="<?=$
    0.80
     Ghi
    0.77
    (@"%@",
    0.76
    haca
    0.76
     Pristupljeno
    0.76
     Osborne
    0.75
     Савез
    0.75
     AssemblyCompany
    0.73
    antina
    0.73
    Activations Density 0.041%

    No Known Activations