© 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. 9383
    Prev
    Next
    INDEX
    Explanations

    names and titles related to military service and honorifics

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

    Followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    military units and formations

    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
     TVA
    -0.54
     congressional
    -0.52
     برانيه
    -0.48
     Theil
    -0.48
    焦
    -0.47
     سف
    -0.46
     Congress
    -0.45
    DispatchToProps
    -0.45
     Congressional
    -0.45
    ưỡi
    -0.44
    POSITIVE LOGITS
    OGND
    0.75
    Nazionale
    0.64
    脚注の使い方
    0.61
     ویکی‌پدیا
    0.60
    AntiForgeryToken
    0.59
    __':
    0.59
     насељу
    0.58
     الملك
    0.56
    )':
    0.55
     Sign
    0.54
    Activations Density 0.178%

    No Known Activations