© 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. 10271
    Prev
    Next
    INDEX
    Explanations

    phrases related to structural or functional elements in a detailed system or process

    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
     InputDecoration
    -0.54
    eradish
    -0.49
    ɵɵ
    -0.48
    ceğine
    -0.47
    ьаж
    -0.45
    Хьажоргаш
    -0.44
    Rüyada
    -0.43
    RTSN
    -0.43
     tantôt
    -0.42
    rungsseite
    -0.42
    POSITIVE LOGITS
     all
    2.11
     semua
    1.98
     모든
    1.83
     every
    1.83
     tutte
    1.81
     todas
    1.80
     wszystkie
    1.78
     wszystkich
    1.77
     kaikki
    1.75
    すべての
    1.73
    Activations Density 1.488%

    No Known Activations