© 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. 2-GEMMASCOPE-RES-16K
    11. 1391
    Prev
    Next
    INDEX
    Explanations

    references to failure or shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BeautifulSoup
    -0.76
    بوابة
    -0.66
    OGND
    -0.66
     Мексичка
    -0.65
    )}
    -0.64
    WebElementEntity
    -0.62
    yntaxException
    -0.61
    ————————————
    -0.60
     通販
    -0.60
    Soup
    -0.60
    POSITIVE LOGITS
     fail
    3.03
     failed
    2.88
     fails
    2.83
     failure
    2.77
     Fail
    2.68
     failing
    2.57
    fail
    2.54
     FAIL
    2.51
    failed
    2.50
     Failure
    2.50
    Activations Density 0.133%

    No Known Activations