© 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. 6750
    Prev
    Next
    INDEX
    Explanations

    concepts related to performance metrics and improvements

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

    Quantifiable improvements or deficiencies

    np_acts-logits-general · gemini-2.0-flash

    metrics and discrepancies

    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
    Ẫ
    -0.50
     órgãos
    -0.49
     circonst
    -0.48
    consulté
    -0.47
     peuples
    -0.46
    NESS
    -0.46
     humeur
    -0.46
     vieilles
    -0.44
    området
    -0.44
     doby
    -0.43
    POSITIVE LOGITS
    bootstrapcdn
    0.84
     gap
    0.82
     explosion
    0.81
     imbalance
    0.76
     difference
    0.75
     shortage
    0.75
     breakthrough
    0.74
     differences
    0.73
     shortfall
    0.73
     upgrades
    0.73
    Activations Density 1.181%

    No Known Activations