© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7146
    Prev
    Next
    INDEX
    Explanations

    themes related to legal terminology and constitutional matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    Con
    -0.38
     Absch
    -0.32
     Con
    -0.31
     than
    -0.31
    SerializedName
    -0.31
     How
    -0.29
     You
    -0.29
    рование
    -0.28
     con
    -0.28
     
    -0.28
    POSITIVE LOGITS
    cons
    2.48
     Cons
    2.41
    Cons
    2.39
     cons
    2.30
     kons
    2.20
     Kons
    2.02
    Kons
    1.91
     CONS
    1.82
    kons
    1.80
     Consortium
    1.73
    Activations Density 0.212%

    No Known Activations