© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 10550
    Prev
    Next
    INDEX
    Explanations

    instances of the word "support" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fleming
    -0.74
     Latimer
    -0.72
    ValueStyle
    -0.71
     ModelExpression
    -0.70
    JDK
    -0.69
    Hg
    -0.69
     Jes
    -0.68
    ogado
    -0.66
     Vegas
    -0.66
    Vegas
    -0.65
    POSITIVE LOGITS
     support
    1.28
     Support
    1.15
    Support
    1.13
     supports
    1.10
     Supports
    1.06
    support
    1.04
     SUPPORT
    1.02
    Supports
    0.99
    supports
    0.98
    ISupport
    0.96
    Activations Density 0.083%

    No Known Activations