© 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. 37-GEMMASCOPE-RES-16K
    11. 5686
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to legal terms and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.41
    rrggbb
    -0.40
     незавершена
    -0.34
    bcryptjs
    -0.34
    互联网档案馆
    -0.32
    atég
    -0.31
     arqu
    -0.31
     MainAxisSize
    -0.30
    onViewCreated
    -0.30
     undated
    -0.30
    POSITIVE LOGITS
     allowed
    2.78
     permitted
    2.63
     Allowed
    2.44
    allowed
    2.38
    Allowed
    2.30
     allowable
    2.28
     permissible
    2.22
     ALLOWED
    2.13
    permitted
    2.05
     permitido
    1.94
    Activations Density 0.977%

    No Known Activations