© 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. 37
    Prev
    Next
    INDEX
    Explanations

    notable phrases or nouns associated with events or organizations

    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
     enkelte
    -0.62
     nødven
    -0.60
     einzelne
    -0.57
     einzelnen
    -0.56
     poszczegól
    -0.50
     others
    -0.50
     singola
    -0.50
     souffrance
    -0.49
     weitere
    -0.48
     Einzelnen
    -0.48
    POSITIVE LOGITS
     famous
    0.81
     famed
    0.80
     popular
    0.78
     infamous
    0.77
     notorious
    0.72
     renowned
    0.70
    famous
    0.70
    popular
    0.66
     controversial
    0.63
     prestigious
    0.62
    Activations Density 0.912%

    No Known Activations