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. 17-GEMMASCOPE-RES-16K
    6. 5077
    Prev
    Next
    INDEX
    Explanations

    terms related to aviation regulations and pilot certification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.07
     “
    -0.80
     ‘
    -0.74
     I
    -0.73
     "
    -0.72
    <eos>
    -0.71
    -
    -0.71
     just
    -0.70
      
    -0.69
     v
    -0.68
    POSITIVE LOGITS
     fubject
    1.55
     purpoſe
    1.45
     Majefty
    1.44
     pleaſure
    1.42
     itſelf
    1.42
     Efq
    1.40
     reaſon
    1.40
     raiſ
    1.39
     ་་
    1.39
     perfons
    1.38
    Activations Density 1.456%

    No Known Activations