© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7832
    Prev
    Next
    INDEX
    Explanations

    numeric data or statistical references

    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
     CTS
    -0.80
     Caron
    -0.71
     Beverly
    -0.68
     Pontiac
    -0.67
    Beverly
    -0.66
     Jamal
    -0.64
    CTS
    -0.58
     Marisa
    -0.58
     Frisch
    -0.57
     CEP
    -0.57
    POSITIVE LOGITS
    uParam
    0.72
     Barrow
    0.68
     Kakashi
    0.67
     Anja
    0.65
     Bowser
    0.64
     Rutherford
    0.61
     Zelda
    0.60
     Tutu
    0.59
     Vicky
    0.59
     Kirby
    0.59
    Activations Density 2.240%

    No Known Activations