© 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. 8567
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to quantum mechanics and information theory.

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

    Scale/bit and dependent/error

    np_acts-logits-general · gemini-2.0-flash

    scale-dependent error probability

    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
    regler
    -0.49
    intermediate
    -0.49
    נר
    -0.48
     suitors
    -0.48
     artysty
    -0.47
     unarmed
    -0.47
     testifying
    -0.47
    hér
    -0.47
    níků
    -0.47
    Investments
    -0.47
    POSITIVE LOGITS
    XmlAccessType
    0.74
    wise
    0.74
    TypedDataSet
    0.74
    例文帳に追加
    0.72
     autorytatywna
    0.72
    ThroughAttribute
    0.70
     дописавши
    0.70
    SizeF
    0.69
     pinulongan
    0.67
    adaptiveStyles
    0.67
    Activations Density 2.130%

    No Known Activations