© 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. 15-GEMMASCOPE-RES-16K
    6. 3728
    Prev
    Next
    INDEX
    Explanations

    references to "Tri" and its variations 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 @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.80
    displayquote
    -0.78
    phous
    -0.72
    inheritDoc
    -0.72
    peutic
    -0.71
    unton
    -0.71
    <*
    -0.69
    Datuak
    -0.69
    ."</
    -0.69
    findpost
    -0.68
    POSITIVE LOGITS
     TRI
    1.15
     Tripp
    1.10
     Tri
    0.97
     TRIP
    0.91
     Tripoli
    0.89
     Trix
    0.89
    Tril
    0.88
    Tri
    0.88
     Trist
    0.87
     trie
    0.86
    Activations Density 0.387%

    No Known Activations