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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 11482
    Prev
    Next
    INDEX
    Explanations

    chemical reactions involving metal complexes and their effects on synthesis processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Traffic
    -0.41
    packing
    -0.40
     Мексичка
    -0.39
    Traffic
    -0.38
     assise
    -0.38
    ština
    -0.37
     anpass
    -0.37
     traffic
    -0.37
     trafik
    -0.37
     TRAFFIC
    -0.37
    POSITIVE LOGITS
     reaction
    1.24
     reactions
    1.16
     Reaction
    1.05
    reaction
    1.00
    Reaction
    0.99
     réaction
    0.98
     Reactions
    0.96
    reactions
    0.95
     reacting
    0.95
     react
    0.93
    Activations Density 1.683%

    No Known Activations