© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8233
    Prev
    Next
    INDEX
    Explanations

    references to opponents or adversaries in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.81
    ########.
    -0.66
    TagMode
    -0.59
    WebServlet
    -0.57
    ContentLoaded
    -0.54
    haikusbot
    -0.52
    Parcelize
    -0.51
    curated
    -0.50
    Clik
    -0.49
    MutableLiveData
    -0.49
    POSITIVE LOGITS
     opponent
    2.86
     opponents
    2.70
    opponent
    2.25
     enemy
    2.08
     Gegner
    1.94
     adversary
    1.91
     enemies
    1.88
     adversaries
    1.88
    Opponent
    1.84
     foes
    1.71
    Activations Density 0.145%

    No Known Activations