© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 9776
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to constitutional law and oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orchester
    -0.42
     officielles
    -0.41
     épouse
    -0.40
     niebla
    -0.40
     herencia
    -0.40
     París
    -0.39
    プローチ
    -0.39
     importación
    -0.39
     montaña
    -0.39
     cabecera
    -0.39
    POSITIVE LOGITS
     Cons
    3.75
    Cons
    3.69
     cons
    3.56
    cons
    3.45
     kons
    2.86
     Kons
    2.78
    Kons
    2.64
     CONS
    2.50
    CONS
    2.33
    kons
    2.31
    Activations Density 0.239%

    No Known Activations