© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 3411
    Prev
    Next
    INDEX
    Explanations

    references to proximity or location of objects or people in relation to one another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.88
     Houſe
    -0.85
    ſelf
    -0.82
     pleaſure
    -0.82
     purpoſe
    -0.80
     Majefty
    -0.80
    脚注の使い方
    -0.79
     Diſ
    -0.76
    ſelves
    -0.76
     perſon
    -0.76
    POSITIVE LOGITS
     beside
    0.97
     obok
    0.95
     adjacent
    0.85
     accanto
    0.81
     opposite
    0.79
     рядом
    0.78
     Beside
    0.78
     nearby
    0.74
     vicino
    0.71
    Nearby
    0.71
    Activations Density 0.176%

    No Known Activations