© 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. 23-GEMMASCOPE-RES-16K
    11. 13156
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and structures associated with data handling and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.52
    InjectAttribute
    -0.52
    ГЛА
    -0.51
    ThroughAttribute
    -0.50
     Viitattu
    -0.49
    fjspx
    -0.49
    zepam
    -0.49
    rishnan
    -0.47
    LogFactory
    -0.46
     saites
    -0.46
    POSITIVE LOGITS
     model
    4.40
    model
    3.93
     Model
    3.48
     MODEL
    3.33
    Model
    3.22
     models
    3.12
     modelo
    3.10
     modèle
    3.05
    MODEL
    2.96
     모델
    2.90
    Activations Density 0.438%

    No Known Activations