© 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. 1-GEMMASCOPE-RES-16K
    11. 8752
    Prev
    Next
    INDEX
    Explanations

    terms related to biology and anatomy, particularly those involving the prefix "Tra" or related to tissue structures

    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
     snippetHide
    -0.66
    AndEndTag
    -0.54
     Numerade
    -0.52
    GetLength
    -0.49
     kasarigan
    -0.49
     OnInit
    -0.49
    Ծանոթ
    -0.48
     Constructor
    -0.47
     BIBSYS
    -0.47
     hObject
    -0.47
    POSITIVE LOGITS
     Tra
    2.19
    Tra
    2.11
     tra
    2.08
    tra
    1.96
     TRA
    1.34
     тра
    1.25
     Тра
    1.20
    トラ
    1.18
    trak
    1.08
    TRA
    1.06
    Activations Density 0.301%

    No Known Activations