© 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. 1-GEMMASCOPE-RES-16K
    11. 2714
    Prev
    Next
    INDEX
    Explanations

    negations and phrases indicating something does not occur or is not true

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     increí
    -0.90
     Geiſt
    -0.87
     dieſe
    -0.86
     Geſch
    -0.85
     يتيمه
    -0.85
     ſeine
    -0.83
     müſſen
    -0.82
     miniaturka
    -0.80
     témoig
    -0.80
     zuſammen
    -0.79
    POSITIVE LOGITS
    .
    0.67
    ↵
    0.66
     
    0.63
    <bos>
    0.60
    ↵↵
    0.56
     "
    0.56
    ,
    0.54
     (
    0.51
        
    0.47
    :
    0.47
    Activations Density 0.241%

    No Known Activations