© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11326
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to contract claims and warranties

    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
    didReceive
    -0.34
    irim
    -0.30
     Hello
    -0.30
    ichtigung
    -0.28
    Hello
    -0.28
     sash
    -0.28
    Hal
    -0.28
    xp
    -0.28
    cshtml
    -0.28
     sach
    -0.28
    POSITIVE LOGITS
     dependence
    3.27
     depend
    3.13
     dependency
    3.03
     dependent
    2.92
     depended
    2.88
     Dependence
    2.88
     dependen
    2.69
     dépend
    2.67
     dependencies
    2.64
    dependence
    2.63
    Activations Density 1.239%

    No Known Activations