© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 13326
    Prev
    Next
    INDEX
    Explanations

    references to intelligence or intelligent behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Walkover
    -0.80
     disambiguazione
    -0.73
     kasarigan
    -0.72
    ngths
    -0.72
     للاسماء
    -0.71
     SwitchCompat
    -0.70
     odkazy
    -0.68
    Tikang
    -0.68
    )_/¯
    -0.67
     Normdatei
    -0.66
    POSITIVE LOGITS
     intelligent
    1.09
    Intelligent
    1.04
     Intelligent
    1.02
    intelligent
    0.90
     intelligently
    0.80
     intelligente
    0.73
     intellig
    0.65
    beginPath
    0.62
     intelligen
    0.61
     inteligente
    0.60
    Activations Density 0.202%

    No Known Activations