© 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. 33-GEMMASCOPE-RES-16K
    11. 10295
    Prev
    Next
    INDEX
    Explanations

    references to organizations, particularly associations related to law enforcement and trade

    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
     مفص
    -0.36
    ViewFeatures
    -0.32
    yntaxException
    -0.29
     Dirac
    -0.28
     skj
    -0.28
    occuper
    -0.25
     verf
    -0.25
    🇰
    -0.25
    clone
    -0.25
    Conclusie
    -0.25
    POSITIVE LOGITS
     association
    1.92
     associations
    1.88
     Association
    1.82
    Association
    1.78
     Associations
    1.71
    association
    1.70
     ASSOCIATION
    1.63
    associations
    1.58
    Associations
    1.53
     Assn
    1.42
    Activations Density 0.393%

    No Known Activations