© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5344
    Prev
    Next
    INDEX
    Explanations

    phrases related to equipment and tools used in construction and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.81
    Portail
    -0.75
     Monfieur
    -0.71
    Geplaatst
    -0.70
     Majefty
    -0.69
     purpoſe
    -0.69
    awtextra
    -0.68
     nahilalakip
    -0.68
    rrggbb
    -0.67
    ]--;
    -0.67
    POSITIVE LOGITS
     rope
    1.01
     cable
    0.96
     cables
    0.91
     Cable
    0.88
     ropes
    0.87
    Cable
    0.86
     Rope
    0.81
    Rope
    0.80
    cable
    0.79
     Cables
    0.76
    Activations Density 0.576%

    No Known Activations