© 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. 5445
    Prev
    Next
    INDEX
    Explanations

    specific product or system names related to medical or technical equipment

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

    Medical or scientific equipment names

    np_acts-logits-general · gemini-2.0-flash

    product names and identifiers

    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
    NameInMap
    -1.13
     saites
    -1.04
     ویکی‌پدیا
    -1.03
    MessageOf
    -0.97
    featureID
    -0.92
    Билгалдахарш
    -0.92
     nahilalakip
    -0.92
    Personensuche
    -0.89
    UnsafeEnabled
    -0.89
    IUrlHelper
    -0.89
    POSITIVE LOGITS
     II
    1.18
     Plus
    1.12
     III
    0.98
    II
    0.91
    Plus
    0.90
     series
    0.85
     Pro
    0.83
    plus
    0.81
     plus
    0.77
     PLUS
    0.77
    Activations Density 0.515%

    No Known Activations