© 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. 41-GEMMASCOPE-RES-16K
    11. 10352
    Prev
    Next
    INDEX
    Explanations

    regulatory language pertaining to compliance and legal directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     many
    -0.67
     birçok
    -0.63
    many
    -0.63
     manchen
    -0.61
     biraz
    -0.61
     some
    -0.61
     muitos
    -0.60
     MANY
    -0.60
     många
    -0.59
     trochę
    -0.59
    POSITIVE LOGITS
     shall
    0.95
    shall
    0.80
     whenever
    0.80
     wherever
    0.79
     preferably
    0.69
    whenever
    0.69
     Wherever
    0.68
     appropriate
    0.68
     adequate
    0.68
     suitably
    0.67
    Activations Density 0.797%

    No Known Activations