© 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. 12176
    Prev
    Next
    INDEX
    Explanations

    references to the concept of honor

    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
    äld
    -0.60
    izop
    -0.55
     eslint
    -0.55
     Avril
    -0.54
    pses
    -0.54
    icoot
    -0.53
    wiek
    -0.53
     naselje
    -0.53
     Cyclops
    -0.52
    arschijnlijk
    -0.51
    POSITIVE LOGITS
     honor
    3.46
     honour
    3.15
    honor
    3.10
     Honor
    3.10
     HONOR
    3.10
    Honor
    3.01
     honors
    2.98
     Honour
    2.77
     honored
    2.63
     honours
    2.54
    Activations Density 0.059%

    No Known Activations