© 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. 27-GEMMASCOPE-RES-16K
    11. 9749
    Prev
    Next
    INDEX
    Explanations

    negative descriptors related to conditions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Züge
    -0.47
     ciepła
    -0.38
    fromnode
    -0.36
    phosa
    -0.36
     tabung
    -0.35
    lète
    -0.34
     veremos
    -0.34
    Koordinaten
    -0.34
    iyor
    -0.34
    ărilor
    -0.34
    POSITIVE LOGITS
     bad
    1.08
     Bad
    1.02
    Bad
    0.97
     BAD
    0.93
    bad
    0.92
    BAD
    0.85
     badly
    0.65
     mauvais
    0.62
     mauvaise
    0.57
     luck
    0.57
    Activations Density 0.084%

    No Known Activations