© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4015
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to the prefix "tri-" or three-part structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hiểm
    -0.39
     intptr
    -0.36
    SerializedSize
    -0.34
    čenje
    -0.33
     sấy
    -0.33
    Personendaten
    -0.32
    gebob
    -0.30
    eneuve
    -0.30
    botten
    -0.30
    LabelTagHelper
    -0.30
    POSITIVE LOGITS
     tri
    4.13
     Tri
    4.06
    Tri
    3.80
    tri
    3.41
     TRI
    2.78
    Tril
    2.44
    TRI
    2.38
     triad
    2.05
     Три
    2.05
     три
    1.90
    Activations Density 0.245%

    No Known Activations