© 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. 3-GEMMASCOPE-RES-16K
    11. 3942
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations or scientific terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.51
     allAfrica
    -0.40
    中略
    -0.37
    SharedCtor
    -0.37
    ंदीखरीदारी
    -0.36
    teries
    -0.35
     Paints
    -0.35
    roir
    -0.35
     shades
    -0.35
     didik
    -0.35
    POSITIVE LOGITS
    va
    1.95
    VA
    1.52
    Va
    1.50
     Va
    1.48
     va
    1.45
     VA
    1.20
    ava
    0.80
    AVA
    0.79
    iva
    0.73
     vaults
    0.70
    Activations Density 1.227%

    No Known Activations