© 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. 0-GEMMASCOPE-RES-16K
    11. 9708
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to database management and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiſ
    -0.92
     pleaſure
    -0.89
     itſelf
    -0.87
     Shaksp
    -0.86
     houſe
    -0.85
     purpoſe
    -0.85
     Anſ
    -0.83
    DeleteBehavior
    -0.83
     Houſe
    -0.82
     Monfieur
    -0.82
    POSITIVE LOGITS
     ox
    0.61
     Henderson
    0.60
     fair
    0.57
     Mus
    0.57
     Fair
    0.56
    INLINE
    0.56
    ux
    0.55
     Williamson
    0.54
     Z
    0.54
    x
    0.54
    Activations Density 3.015%

    No Known Activations