© 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. 6-GEMMASCOPE-RES-16K
    11. 11435
    Prev
    Next
    INDEX
    Explanations

    words related to suitability or correctness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RLock
    -0.69
    ad
    -0.64
    Din
    -0.61
    FieldBuilder
    -0.61
    rboles
    -0.60
    HashCode
    -0.59
     kil
    -0.59
     Kil
    -0.59
     venden
    -0.58
     الحره
    -0.57
    POSITIVE LOGITS
    Appropriate
    1.93
     Appropriate
    1.85
     appropriate
    1.80
    appropriate
    1.72
    nappropriate
    1.68
     appropriately
    1.57
     APPROPRI
    1.50
     appropri
    1.47
    Inappropriate
    1.46
     inappropriate
    1.39
    Activations Density 0.088%

    No Known Activations