© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 9082
    Prev
    Next
    INDEX
    Explanations

    words relating to mental states and emotional conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.43
     nakalista
    -0.41
    esModule
    -0.36
     viktig
    -0.35
    adaptiveStyles
    -0.35
     Auswirkungen
    -0.33
    openzeppelin
    -0.33
    🇶
    -0.33
     сов
    -0.32
     invloed
    -0.32
    POSITIVE LOGITS
     characterize
    1.25
     characterizes
    1.23
     characterized
    1.15
     characterised
    1.09
    character
    1.02
     character
    1.01
     caratter
    0.99
     caracter
    0.98
     caractéris
    0.97
     caracteriza
    0.94
    Activations Density 0.593%

    No Known Activations