© 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. 35-GEMMASCOPE-RES-16K
    11. 13073
    Prev
    Next
    INDEX
    Explanations

    references to actions of giving, telling, and authority figures in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    himself
    -0.81
    setupUi
    -0.78
     himſelf
    -0.77
     himself
    -0.76
     그는
    -0.72
    彼は
    -0.71
     Himself
    -0.68
     خودش
    -0.66
     EconPapers
    -0.64
     उसने
    -0.63
    POSITIVE LOGITS
     him
    0.91
     им
    0.91
     אותו
    0.80
     τον
    0.79
     ihn
    0.69
    ándolo
    0.57
     honom
    0.56
     hä
    0.54
     im
    0.53
     jej
    0.53
    Activations Density 0.159%

    No Known Activations