© 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. 11-GEMMASCOPE-RES-16K
    11. 10173
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare and treatment options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bahía
    -0.59
     montanha
    -0.59
     reaccion
    -0.59
     cuchara
    -0.58
     zví
    -0.57
     desmotivaciones
    -0.56
     encuesta
    -0.56
     indietro
    -0.56
    étranger
    -0.56
     infancia
    -0.56
    POSITIVE LOGITS
     autorytatywna
    0.62
    becomes
    0.47
    instead
    0.46
     becomes
    0.45
     instead
    0.45
    了呢
    0.41
    敷
    0.41
    abestanden
    0.40
     become
    0.40
    事
    0.39
    Activations Density 1.054%

    No Known Activations