© 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. 41-GEMMASCOPE-RES-16K
    11. 10147
    Prev
    Next
    INDEX
    Explanations

    action verbs and phrases related to investigation and analysis

    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
     které
    -0.55
     sendo
    -0.54
     ktore
    -0.51
     offrant
    -0.48
    nezeu
    -0.47
     Мексичка
    -0.46
     która
    -0.46
     който
    -0.45
     jotka
    -0.45
     используя
    -0.45
    POSITIVE LOGITS
     separately
    1.00
     in
    0.98
     simultaneously
    0.98
     directly
    0.94
     briefly
    0.92
     mainly
    0.90
     exclusively
    0.89
     primarily
    0.89
     annually
    0.88
     the
    0.87
    Activations Density 1.771%

    No Known Activations