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 - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 10844
    Prev
    Next
    INDEX
    Explanations

    phrases related to recognition and achievement in education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.85
     NSCoder
    -0.84
     متعلقه
    -0.76
    Vidite
    -0.74
    ंदीखरीदारी
    -0.74
     himo
    -0.72
    PyExc
    -0.71
    彿
    -0.70
     lenker
    -0.70
    urlopen
    -0.68
    POSITIVE LOGITS
     achievements
    0.74
     accomplishments
    0.71
     outstanding
    0.65
     exceptionnelle
    0.61
     logros
    0.60
     exemplary
    0.59
     exceptionnel
    0.55
    ítmény
    0.55
    outstanding
    0.55
     deserving
    0.55
    Activations Density 0.138%

    No Known Activations