© 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. 8559
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to biochemical or biological processes

    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
     sobie
    -0.36
    msgSender
    -0.35
     sengaja
    -0.34
     wikipagina
    -0.33
    hilangan
    -0.32
     kogo
    -0.32
    accueil
    -0.32
     choix
    -0.31
    atería
    -0.31
     mierda
    -0.31
    POSITIVE LOGITS
    ued
    1.13
    ue
    1.13
    uc
    1.10
    ude
    1.02
    uj
    1.01
    ute
    1.01
    uf
    1.00
    uz
    0.98
    uh
    0.96
    uw
    0.96
    Activations Density 1.262%

    No Known Activations