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. 3-GEMMASCOPE-RES-16K
    6. 12244
    Prev
    Next
    INDEX
    Explanations

    instances of the word "most" indicating a superlative or comparative context

    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
     оригіналу
    -0.97
    VideoCapture
    -0.86
     Efq
    -0.84
     Anſ
    -0.82
     Cluj
    -0.81
     ſche
    -0.80
     ſta
    -0.79
    eraard
    -0.79
     houſe
    -0.77
     ejus
    -0.76
    POSITIVE LOGITS
     most
    1.61
    most
    1.16
     meest
    1.02
     more
    1.02
     Most
    1.01
    Most
    0.99
    MOST
    0.98
     MOST
    0.97
     najbardziej
    0.87
     highest
    0.86
    Activations Density 0.048%

    No Known Activations