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. 6-GEMMASCOPE-RES-16K
    6. 2360
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "way."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -1.10
     ―――――
    -1.07
     Monfieur
    -1.06
     Majefty
    -1.02
     pleaſure
    -1.01
     myſelf
    -0.99
    вгений
    -0.99
     Theſe
    -0.98
     Inſ
    -0.98
     preſent
    -0.98
    POSITIVE LOGITS
     way
    2.09
     Way
    2.07
     WAY
    2.00
    Way
    1.91
    way
    1.80
     ways
    1.78
     Ways
    1.67
    WAY
    1.64
     WAYS
    1.61
    Ways
    1.53
    Activations Density 0.071%

    No Known Activations