© 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. 11-GEMMASCOPE-RES-16K
    11. 11708
    Prev
    Next
    INDEX
    Explanations

    references to themes of guilt and redemption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.68
    +#+#
    -0.66
     EconPapers
    -0.61
     surla
    -0.60
    asantry
    -0.59
    
    -0.59
     autorytatywna
    -0.57
    estimable
    -0.57
     sundry
    -0.56
    Magnet
    -0.56
    POSITIVE LOGITS
     pitié
    0.36
     hurt
    0.32
    FormTagHelper
    0.30
     protect
    0.29
    úgó
    0.29
     mancha
    0.28
    RTCF
    0.28
     proteger
    0.28
     lágrimas
    0.28
     sexual
    0.26
    Activations Density 0.437%

    No Known Activations