© 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. 14316
    Prev
    Next
    INDEX
    Explanations

    tax-related terms and financial reporting terminology

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

    Tokens after common punctuation

    np_acts-logits-general · gemini-2.0-flash

    lists of specific items or abbreviations

    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
     ActiveRecord
    -0.51
    Geplaatst
    -0.50
    XPATH
    -0.48
     justement
    -0.48
    OpenHelper
    -0.47
    édric
    -0.47
    subtitle
    -0.47
    ț
    -0.46
    闌
    -0.46
    NegativeButton
    -0.46
    POSITIVE LOGITS
    などなど
    1.08
     etc
    1.01
    })();
    0.95
    """.
    0.92
     purpoſe
    0.88
     ſeveral
    0.87
     leaſt
    0.87
    <eos>
    0.87
     }}"></
    0.87
     lastly
    0.86
    Activations Density 0.672%

    No Known Activations