© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 2158
    Prev
    Next
    INDEX
    Explanations

    terms associated with football position descriptors and defensive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.59
    thâu
    -0.55
    Autoritní
    -0.55
    ⓧ
    -0.55
    }^{+\
    -0.51
    Gambas
    -0.50
     baskets
    -0.48
     Baskets
    -0.48
    ГЛА
    -0.47
    ंदीखरीदारी
    -0.47
    POSITIVE LOGITS
     defensive
    1.06
     defensively
    0.97
     Defensive
    0.91
     defender
    0.90
     protection
    0.89
     protecting
    0.86
     defense
    0.85
     defence
    0.85
    Defensive
    0.85
     Protecting
    0.84
    Activations Density 0.376%

    No Known Activations