© 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. 23-GEMMASCOPE-RES-16K
    11. 6857
    Prev
    Next
    INDEX
    Explanations

    references to gender differences in educational or performance contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.72
    sidemargin
    -0.47
     Paglinawan
    -0.46
     الحره
    -0.45
    celotti
    -0.43
    zwungen
    -0.41
     resourceCulture
    -0.41
    InitStruct
    -0.40
     Neutral
    -0.40
     Threads
    -0.39
    POSITIVE LOGITS
     differences
    1.36
    Differences
    1.19
     difference
    1.17
     Differences
    1.16
    differences
    1.15
     Unterschiede
    1.13
     différences
    1.04
     diferencias
    1.02
     différence
    0.98
     Difference
    0.96
    Activations Density 1.765%

    No Known Activations