© 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. 12425
    Prev
    Next
    INDEX
    Explanations

    mentions of military or intelligence units and their operational details

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

    "... Air Force Base"

    np_acts-logits-general · gemini-2.0-flash

    air force bases

    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
     NSCoder
    -0.63
    omitempty
    -0.56
     henvisninger
    -0.56
    abetes
    -0.55
     pinulongan
    -0.54
    ObjectMeta
    -0.53
    NewUrlParser
    -0.51
    ListItemIcon
    -0.50
     disambiguazione
    -0.50
     BoxDecoration
    -0.49
    POSITIVE LOGITS
     base
    0.97
     Base
    0.94
     bases
    0.86
    base
    0.81
    Base
    0.80
     Bases
    0.77
    bases
    0.74
     AFB
    0.70
     Installation
    0.70
     getBase
    0.69
    Activations Density 0.148%

    No Known Activations