© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 2436
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to discussions and debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réussite
    -0.63
    verläs
    -0.57
     malheur
    -0.56
    Viki
    -0.54
     TAMBÉM
    -0.54
     Palmas
    -0.53
    addComponent
    -0.52
    шенко
    -0.52
    tidae
    -0.50
     Picchu
    -0.50
    POSITIVE LOGITS
     discussion
    1.50
     discussions
    1.45
    discussion
    1.24
     debates
    1.22
     debate
    1.21
     Discussions
    1.21
     conversations
    1.19
     discus
    1.16
     conversation
    1.15
    Discussions
    1.14
    Activations Density 0.042%

    No Known Activations