© 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. 3-GEMMASCOPE-RES-16K
    11. 8655
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement units or numerical values

    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
     urusan
    -0.31
    farwydd
    -0.27
    령
    -0.26
     wę
    -0.26
    OPLE
    -0.25
     burung
    -0.25
     espirituales
    -0.25
     almendras
    -0.25
     antemano
    -0.24
     skå
    -0.24
    POSITIVE LOGITS
     pon
    1.50
     Pon
    1.47
     Penn
    1.45
    Pon
    1.45
     Penny
    1.42
     pen
    1.40
     Пен
    1.39
    Penn
    1.38
     Pen
    1.37
     PEN
    1.37
    Activations Density 1.198%

    No Known Activations