Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12278
    Prev
    Next
    INDEX
    Explanations

    expressions related to strategies and strategic planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueGeneration
    -0.99
    contentLoaded
    -0.83
    انجليز
    -0.80
    Datuak
    -0.79
    phous
    -0.75
     Cytometry
    -0.75
     femeninos
    -0.75
    NameInMap
    -0.73
    sticks
    -0.73
    GeneratedValue
    -0.73
    POSITIVE LOGITS
     strategies
    1.54
     Strategies
    1.42
    strategies
    1.34
     strategy
    1.33
    Strategies
    1.29
    Strategy
    1.21
     Strategy
    1.21
    strategy
    1.14
    Strat
    1.13
     STRATEGY
    1.09
    Activations Density 0.039%

    No Known Activations