© 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. 2-GEMMASCOPE-RES-16K
    11. 7899
    Prev
    Next
    INDEX
    Explanations

    words related to "tree" or similar-sounding terms

    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
    锈钢
    -0.52
     صوتيه
    -0.50
     varandra
    -0.47
     تضيفلها
    -0.46
    irinha
    -0.46
     encuent
    -0.46
     للاسماء
    -0.46
    ↷
    -0.45
     smör
    -0.45
    Materiał
    -0.45
    POSITIVE LOGITS
     tre
    1.05
     Tre
    0.99
    Tre
    0.87
    tre
    0.73
     TRE
    0.67
    setVerticalGroup
    0.63
    者
    0.58
     Soviet
    0.51
    TRE
    0.49
    клопе
    0.46
    Activations Density 0.498%

    No Known Activations