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. 4-GEMMASCOPE-RES-16K
    6. 977
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Royce
    -0.56
    Referencies
    -0.55
     UNI
    -0.54
     Reef
    -0.51
     CWE
    -0.51
    Numerology
    -0.49
     roach
    -0.48
     Kampala
    -0.48
     panelists
    -0.47
     Sodom
    -0.47
    POSITIVE LOGITS
    THAT
    1.27
    That
    1.21
     That
    1.19
     THAT
    1.14
    that
    1.01
     ese
    0.92
    Those
    0.87
     esa
    0.86
     Those
    0.85
    Thats
    0.84
    Activations Density 0.209%

    No Known Activations