© 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. 37-GEMMASCOPE-RES-16K
    11. 1913
    Prev
    Next
    INDEX
    Explanations

    references to collective experiences and the impact of technology on daily life

    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
     conmigo
    -1.14
     comigo
    -0.90
     me
    -0.72
     itself
    -0.71
     Itself
    -0.70
     mnie
    -0.68
    itself
    -0.66
    私に
    -0.66
     خودش
    -0.63
     benim
    -0.60
    POSITIVE LOGITS
     ourselves
    2.41
     можем
    1.16
     our
    1.14
     będziemy
    1.02
     наших
    0.99
     możemy
    0.98
     знаем
    0.98
     jesteśmy
    0.96
     máme
    0.96
     nossos
    0.93
    Activations Density 0.834%

    No Known Activations