© 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-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10134
    Prev
    Next
    INDEX
    Explanations

    words indicating detailed understanding or analysis

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Theſe
    -1.25
     Monfieur
    -1.25
     itſelf
    -1.24
     Majefty
    -1.23
     Efq
    -1.21
     Shakspeare
    -1.21
     myſelf
    -1.20
     themſelves
    -1.16
     Jefus
    -1.13
     Anſ
    -1.12
    POSITIVE LOGITS
     Al
    0.62
     Kap
    0.61
     understand
    0.60
     detailed
    0.60
     ber
    0.57
     pas
    0.56
     Detailed
    0.55
     Bell
    0.55
    Detailed
    0.55
     [
    0.54
    Activations Density 0.036%

    No Known Activations