© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 9358
    Prev
    Next
    INDEX
    Explanations

    textual references to legal and political concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prioritize
    -0.52
     feas
    -0.48
     fend
    -0.47
     succumb
    -0.47
     aka
    -0.47
     AKA
    -0.46
     prioritise
    -0.45
     prioritizing
    -0.44
    odly
    -0.44
     navigate
    -0.44
    POSITIVE LOGITS
     gewiß
    0.53
     contemporaine
    0.51
     étrangère
    0.50
    IUrlHelper
    0.50
     fût
    0.50
    DIPSETTING
    0.50
     noires
    0.50
     termica
    0.50
     vectorielle
    0.49
     ſtill
    0.49
    Activations Density 0.703%

    No Known Activations