© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5875
    Prev
    Next
    INDEX
    Explanations

    variations of the word "way" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.17
     ―――――
    -1.16
    PerformLayout
    -1.14
     pleaſure
    -1.08
     Majefty
    -1.08
     Inſ
    -1.06
     myſelf
    -1.05
    вгений
    -1.03
     Chriſt
    -1.01
     preſent
    -1.01
    POSITIVE LOGITS
     way
    3.23
     Way
    3.04
    Way
    2.89
     WAY
    2.87
    way
    2.75
    WAY
    2.49
     ways
    2.40
     Ways
    2.19
     WAYS
    2.07
    Ways
    2.07
    Activations Density 0.072%

    No Known Activations