© 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. 9-GEMMASCOPE-RES-16K
    11. 9196
    Prev
    Next
    INDEX
    Explanations

    instances of the word "write" and its variations, indicating a focus on writing actions or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trop
    -0.58
    ganggu
    -0.53
    従
    -0.50
     Cougars
    -0.50
     terecht
    -0.49
     Kang
    -0.48
    )++;
    -0.48
    orghini
    -0.48
    cope
    -0.47
     nemico
    -0.47
    POSITIVE LOGITS
     write
    1.74
    write
    1.66
    Write
    1.56
     Write
    1.55
     writing
    1.50
     Writing
    1.36
    Writing
    1.34
     WRITE
    1.33
    writing
    1.33
     writes
    1.32
    Activations Density 0.126%

    No Known Activations