© 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. 22-GEMMASCOPE-RES-16K
    11. 12748
    Prev
    Next
    INDEX
    Explanations

    references to environmental impacts and proposed regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "the" followed by a country or place

    np_acts-logits-general · gemini-2.0-flash

    "the" + wide domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.69
    CodedInputStream
    -0.65
    AndEndTag
    -0.63
     Roskov
    -0.63
     referenties
    -0.61
     שוליים
    -0.60
     GenerationType
    -0.60
    TestingModule
    -0.60
     LoggerFactory
    -0.60
    Numerade
    -0.59
    POSITIVE LOGITS
     wider
    0.79
    wider
    0.71
     broader
    0.71
     Wider
    0.64
    Wider
    0.57
     broadest
    0.56
    참고
    0.56
     larger
    0.55
     widest
    0.54
    
    0.54
    Activations Density 0.371%

    No Known Activations