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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11598
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the term "dynamic" and its variations, indicating a focus on concepts related to dynamics or dynamic systems

    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
     littéraire
    -0.80
     étrangère
    -0.80
    CloseOperation
    -0.77
     étoit
    -0.77
     Paddington
    -0.75
     végétale
    -0.75
    CrossRef
    -0.72
     Montaigne
    -0.72
     veneta
    -0.71
     TSA
    -0.71
    POSITIVE LOGITS
     dynamic
    2.33
     Dynamic
    2.02
     dynamics
    2.01
    dynamic
    2.01
    Dynamic
    1.94
     DYNAMIC
    1.87
     dynamically
    1.79
    DYNAMIC
    1.78
     dynamique
    1.76
    dynamics
    1.74
    Activations Density 0.076%

    No Known Activations