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

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30028
    Prev
    Next
    INDEX
    Explanations

    terms related to tactical operations and strategies

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

    tactics and strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rowData
    -0.71
    currencies
    -0.69
     Bonne
    -0.68
    yue
    -0.67
     Jones
    -0.66
     Italijanski
    -0.65
    enes
    -0.64
     Coney
    -0.64
     fleste
    -0.64
     $[-
    -0.63
    POSITIVE LOGITS
     Tactics
    1.15
     tactics
    1.05
     tactic
    0.82
    ctics
    0.81
     nisso
    0.79
     poichè
    0.78
     Takt
    0.78
     tactical
    0.77
     Talis
    0.77
     Italij
    0.77
    Activations Density 0.019%

    No Known Activations