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. 5-GEMMASCOPE-RES-16K
    6. 5468
    Prev
    Next
    INDEX
    Explanations

    references to inspiration and influences in creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.03
     itſelf
    -1.02
     ſtate
    -0.90
     oprot
    -0.85
     themſelves
    -0.84
     preſent
    -0.83
     purpoſe
    -0.83
    ſelf
    -0.83
     ſever
    -0.81
     himſelf
    -0.81
    POSITIVE LOGITS
    Inspired
    0.74
     Inspired
    0.74
     mimic
    0.72
    inspired
    0.71
     inspired
    0.69
     imit
    0.69
     imitate
    0.68
     inspirations
    0.67
    模仿
    0.66
     copying
    0.65
    Activations Density 0.350%

    No Known Activations