© 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. 33-GEMMASCOPE-RES-16K
    11. 1732
    Prev
    Next
    INDEX
    Explanations

    legal language related to demands and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuspendLayout
    -0.40
    ViewImports
    -0.30
    ThroughAttribute
    -0.27
     /*#__
    -0.27
     JADX
    -0.26
    ssize
    -0.26
     effectuer
    -0.25
    Les
    -0.24
     nemus
    -0.24
    Status
    -0.24
    POSITIVE LOGITS
     demands
    2.69
     demand
    2.67
     demanded
    2.63
    demand
    2.61
     demanding
    2.56
     Demands
    2.47
     DEMAND
    2.41
     Demand
    2.39
    Demand
    2.31
     exigir
    2.03
    Activations Density 0.740%

    No Known Activations