© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11121
    Prev
    Next
    INDEX
    Explanations

    expressions of congratulations and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.80
     noDo
    -0.67
    mybatisplus
    -0.66
    obium
    -0.66
    脚注の使い方
    -0.61
     通販
    -0.61
    WriteTagHelper
    -0.61
     Вікі
    -0.60
    ifrance
    -0.60
    ˏ
    -0.60
    POSITIVE LOGITS
     congratulations
    1.93
     Congratulations
    1.85
    Congratulations
    1.83
     Congrats
    1.69
     congrats
    1.68
    Congrats
    1.62
    Kudos
    1.56
     Kudos
    1.55
     kudos
    1.55
     congratulate
    1.52
    Activations Density 0.135%

    No Known Activations