© 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. 3-GEMMASCOPE-RES-16K
    11. 1926
    Prev
    Next
    INDEX
    Explanations

    references to failures and shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oignons
    -0.67
     Mox
    -0.65
    ">//
    -0.64
    EnableWeb
    -0.63
     GenerationType
    -0.60
    Према
    -0.60
     menyambut
    -0.59
    onion
    -0.59
     dart
    -0.58
     лука
    -0.58
    POSITIVE LOGITS
     failure
    3.41
     Failure
    3.14
    Failure
    2.98
    failure
    2.94
     FAILURE
    2.91
     failures
    2.87
     Failures
    2.54
    FAILURE
    2.52
     failing
    2.34
     fail
    2.32
    Activations Density 0.087%

    No Known Activations