© 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. 14975
    Prev
    Next
    INDEX
    Explanations

    concepts related to simplicity and complexity

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

    followed by adverbs of degree

    np_acts-logits-general · gemini-2.0-flash

    really simple explanations

    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
    SourceChecksum
    -0.52
    RuleContext
    -0.46
    loride
    -0.46
    rvats
    -0.45
     mahdol
    -0.42
    といけない
    -0.41
    zeitig
    -0.41
     &&
    -0.41
    뀔
    -0.41
    JMenu
    -0.41
    POSITIVE LOGITS
     really
    3.39
    really
    3.12
    Really
    2.86
     Really
    2.82
     REALLY
    2.21
     realmente
    2.21
     realy
    2.06
     vraiment
    1.97
     wirklich
    1.96
     naprawdę
    1.76
    Activations Density 0.434%

    No Known Activations