Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53469
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to humility and submission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    humility and modesty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.82
    WriteLiteral
    -0.79
    IContainer
    -0.71
    RegistryLite
    -0.69
    IConfiguration
    -0.68
     насељу
    -0.67
     SqlConnection
    -0.66
    zaki
    -0.65
    WillAppear
    -0.64
     članak
    -0.63
    POSITIVE LOGITS
     Humble
    1.35
    Humble
    1.34
    humble
    1.27
     Humb
    1.20
     humility
    1.16
     humble
    1.15
     humbly
    1.11
     humilde
    1.06
     humbled
    1.05
     humb
    1.03
    Activations Density 0.017%

    No Known Activations