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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8324
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "tri" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    čenje
    -0.38
     hiểm
    -0.35
    망
    -0.33
     naudoti
    -0.32
     hâm
    -0.31
     Kassen
    -0.31
     grasas
    -0.31
     mercancías
    -0.31
     hueso
    -0.30
    botten
    -0.30
    POSITIVE LOGITS
     Tri
    3.75
     tri
    3.66
    Tri
    3.58
    tri
    3.39
     TRI
    2.81
    Tril
    2.47
    TRI
    2.45
     TRIB
    2.20
     Три
    2.11
     Trib
    2.05
    Activations Density 0.219%

    No Known Activations