© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10856
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals and places

    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
    #+#
    -0.85
    IntoConstraints
    -0.83
    Personensuche
    -0.83
    Autoritní
    -0.73
    oredCriteria
    -0.71
     kohdetta
    -0.69
    AccessorTable
    -0.69
    iſchen
    -0.67
    CompilerServices
    -0.67
    tanleria
    -0.66
    POSITIVE LOGITS
     Mengen
    0.28
     either
    0.25
     الحره
    0.24
    ่วน
    0.24
    チール
    0.23
     yaşında
    0.23
     remarqué
    0.22
    /**
    0.22
    เช
    0.22
     pega
    0.22
    Activations Density 0.794%

    No Known Activations