© 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. 11-GEMMASCOPE-RES-16K
    11. 13446
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fight" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     généraux
    -0.84
     supérieurs
    -0.78
     dAtA
    -0.76
     RZ
    -0.76
     placés
    -0.74
     Boon
    -0.73
    Ils
    -0.73
     conséquence
    -0.72
    umbar
    -0.71
    consumers
    -0.71
    POSITIVE LOGITS
    fight
    1.70
     fight
    1.68
     FIGHT
    1.56
     Fight
    1.53
     fights
    1.53
     fought
    1.50
     Fighting
    1.43
    fights
    1.39
     fighting
    1.39
    FIGHT
    1.39
    Activations Density 0.053%

    No Known Activations