© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7301
    Prev
    Next
    INDEX
    Explanations

    elements related to planning and preparation for events or tasks

    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
    windowFixed
    -0.39
    tilhar
    -0.39
    AndroidJUnit
    -0.36
    pyplot
    -0.35
    emlrt
    -0.33
    principalColumn
    -0.33
    odoo
    -0.33
    kloped
    -0.33
    dată
    -0.32
    IsContent
    -0.32
    POSITIVE LOGITS
     preparation
    3.19
     prepare
    3.03
     preparing
    2.91
     prepared
    2.84
     prepares
    2.83
     Preparation
    2.78
     preparations
    2.75
    preparation
    2.72
    prepare
    2.69
     prepar
    2.64
    Activations Density 0.736%

    No Known Activations