© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5534
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical estimation and computational efficiency

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

    Computational cost/complexity

    np_acts-logits-general · gemini-2.0-flash

    computation resolution accuracy complexity

    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
    RegressionTest
    -0.61
     transfieras
    -0.58
    ]")]
    -0.55
    uncher
    -0.55
    culously
    -0.50
    ogli
    -0.49
     INDEPENDENT
    -0.46
    parsedMessage
    -0.45
     Aide
    -0.45
    ământ
    -0.45
    POSITIVE LOGITS
     computational
    0.91
     resolution
    0.84
     complexity
    0.81
     accuracy
    0.70
     generality
    0.70
     performance
    0.70
     precision
    0.66
     gran
    0.63
     Resolution
    0.63
    UAGES
    0.62
    Activations Density 1.180%

    No Known Activations