© 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. 27-GEMMASCOPE-RES-16K
    6. 10248
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures

    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
     Secrétaire
    -0.38
     votación
    -0.35
     compagnon
    -0.35
     Sénat
    -0.34
     drapeau
    -0.34
     constructeur
    -0.34
     amistad
    -0.34
     redacción
    -0.34
     circulación
    -0.33
     cartaz
    -0.33
    POSITIVE LOGITS
     build
    0.74
     perform
    0.69
    build
    0.68
     Build
    0.66
    Build
    0.66
    demar
    0.62
     Perform
    0.59
    ༘
    0.59
     handle
    0.58
     gambe
    0.56
    Activations Density 0.324%

    No Known Activations