© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 6397
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !");
    
    -0.42
     }}$}
    -0.41
    ")){
    
    -0.37
    !")
    
    -0.37
     <",
    -0.37
    \}\\
    -0.35
    :</
    -0.34
    }$}
    -0.34
    ]:
    
    -0.34
    '){
    
    -0.34
    POSITIVE LOGITS
     ainfi
    0.84
     Republican
    0.84
     houſe
    0.82
     film
    0.81
     plufieurs
    0.79
     album
    0.79
     ſtate
    0.79
     Senate
    0.78
     exhibition
    0.77
     ſche
    0.76
    Activations Density 2.216%

    No Known Activations