© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14555
    Prev
    Next
    INDEX
    Explanations

    terms related to allergies and their symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     espelho
    -0.51
     ganadores
    -0.48
     agujeros
    -0.44
     didukung
    -0.43
     kysy
    -0.43
     retrovisor
    -0.42
     bicchiere
    -0.42
     desmotivaciones
    -0.42
     espejos
    -0.42
     proyectos
    -0.42
    POSITIVE LOGITS
     allergies
    0.86
     allergic
    0.85
     allergy
    0.83
     Allergy
    0.77
     Allergies
    0.74
     allergens
    0.71
     allergen
    0.67
     Aller
    0.67
    Aller
    0.67
     alér
    0.65
    Activations Density 0.285%

    No Known Activations