© 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. 6153
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and acronyms related to scientific institutions and research

    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
     विश्वसनीयता
    -0.36
     nắng
    -0.32
    がき
    -0.29
     Fürsten
    -0.29
     digress
    -0.28
     vectorielles
    -0.28
     Beine
    -0.28
    insegna
    -0.27
     Ende
    -0.27
    importanza
    -0.27
    POSITIVE LOGITS
    uxxxx
    0.71
     kaarangay
    0.70
    Tikang
    0.63
     transfieras
    0.62
     Normdatei
    0.60
     cherchés
    0.59
    jsii
    0.57
     Италијани
    0.56
     متعلقه
    0.56
     NSCoder
    0.56
    Activations Density 2.430%

    No Known Activations