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. 260
    Prev
    Next
    INDEX
    Explanations

    references to the word "Ta" and its variations, particularly in a cultural or geographic context related to Tahiti

    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
      
    -0.76
    </h1>
    -0.73
     Lawson
    -0.71
    thom
    -0.69
    ilus
    -0.69
     Miller
    -0.68
     Schlegel
    -0.68
    setProduct
    -0.67
     Moreno
    -0.67
     ws
    -0.66
    POSITIVE LOGITS
     Ta
    1.53
    Ta
    1.52
     TA
    1.32
    ta
    1.30
     ta
    1.28
    TA
    1.27
     Taft
    1.16
     Tape
    1.13
     Tavern
    1.08
     tapes
    1.06
    Activations Density 0.123%

    No Known Activations