© 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. 33-GEMMASCOPE-RES-16K
    11. 11806
    Prev
    Next
    INDEX
    Explanations

    instances of the word "made" and its variations, indicating creation or production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.55
     externes
    -0.41
     Runnable
    -0.40
    ismet
    -0.39
     становника
    -0.39
    Aktualisiert
    -0.39
    IRQn
    -0.37
     Pumps
    -0.37
    englanniksi
    -0.36
     NUKAT
    -0.36
    POSITIVE LOGITS
     entirely
    0.63
    出版年
    0.58
     using
    0.57
     specifically
    0.55
     специально
    0.54
     expressly
    0.53
     utilizzando
    0.53
    specially
    0.52
     specially
    0.52
    specifically
    0.50
    Activations Density 0.310%

    No Known Activations