© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6139
    Prev
    Next
    INDEX
    Explanations

    military ranks and affiliations

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

    Ordinal suffixes (st, nd, rd, th)

    np_acts-logits-general · gemini-2.0-flash

    ordinal numbers followed by military units

    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
     ***!
    -0.54
     yii
    -0.50
     AssemblyProduct
    -0.50
     AFB
    -0.48
     militaires
    -0.47
     beginnetje
    -0.47
    ControllerTest
    -0.47
     militar
    -0.46
     militari
    -0.45
     militaire
    -0.45
    POSITIVE LOGITS
     Battery
    0.84
     battery
    0.80
    Battery
    0.77
     BATTERY
    0.73
    battery
    0.68
    Personendaten
    0.64
     Administrativna
    0.64
     batteries
    0.64
     Company
    0.63
     Companies
    0.62
    Activations Density 0.225%

    No Known Activations