© 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 EvalsExportsinterp-engineNEWAPI 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. 5591
    Prev
    Next
    INDEX
    Explanations

    instances of relationships and connections between people, including friendships and romantic ties

    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
     auprès
    -0.49
     reclamo
    -0.45
    rizona
    -0.44
     ब्रेकडाउन
    -0.44
    Oneof
    -0.42
    Personendaten
    -0.41
    batore
    -0.40
     implor
    -0.39
     CreateTagHelper
    -0.38
     comunit
    -0.38
    POSITIVE LOGITS
     mutual
    1.01
     friendship
    0.99
     mutually
    0.87
     exchanging
    0.82
     amizade
    0.81
    friendship
    0.79
    mutual
    0.78
     exchanged
    0.75
    お互
    0.73
    Mutual
    0.72
    Activations Density 0.405%

    No Known Activations