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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9085
    Prev
    Next
    INDEX
    Explanations

    phrases related to strategies in football and their players

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

    Football offense and systems

    np_acts-logits-general · gemini-2.0-flash

    offense system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Décès
    -0.51
    TextHelper
    -0.47
    ImageContext
    -0.46
    isler
    -0.42
    otonin
    -0.42
    ajuku
    -0.41
    selo
    -0.40
     sva
    -0.40
    ínez
    -0.40
     affari
    -0.40
    POSITIVE LOGITS
     offense
    0.99
     system
    0.88
     Offense
    0.88
     offence
    0.86
     System
    0.81
     schemes
    0.81
     offenses
    0.78
     SYSTEM
    0.78
    system
    0.78
     style
    0.76
    Activations Density 0.134%

    No Known Activations