© 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. 3-GEMMASCOPE-RES-16K
    11. 12216
    Prev
    Next
    INDEX
    Explanations

    instances of the word "compromise" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    ianum
    -0.73
     fubject
    -0.71
     pleaſure
    -0.69
     subjection
    -0.68
     Geller
    -0.65
    ustomed
    -0.64
     Veterin
    -0.61
     goû
    -0.60
     glucocortico
    -0.59
    transQ
    -0.59
    POSITIVE LOGITS
     compromise
    1.10
     compromises
    1.01
    tagHelperRunner
    0.98
     Compromise
    0.96
     resourceCulture
    0.94
    Comprom
    0.91
     compromising
    0.89
     lenker
    0.88
    comprom
    0.88
    ReusableCell
    0.87
    Activations Density 0.105%

    No Known Activations