© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 9058
    Prev
    Next
    INDEX
    Explanations

    terms related to legal defense and the act of defending 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 @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    Tikang
    -0.50
    thâu
    -0.48
    ✨:
    -0.48
    yarnpkg
    -0.47
    multicolumn
    -0.42
    WillAppear
    -0.41
     anom
    -0.40
    People
    -0.39
    otides
    -0.39
     Picker
    -0.38
    POSITIVE LOGITS
     defense
    1.80
     defence
    1.79
    defense
    1.58
    defence
    1.55
     defend
    1.54
     Defense
    1.53
    Defense
    1.53
     Defence
    1.51
     defending
    1.50
     DEFENSE
    1.48
    Activations Density 0.160%

    No Known Activations