© 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. 2-GEMMASCOPE-RES-16K
    11. 8470
    Prev
    Next
    INDEX
    Explanations

    words related to the installation of software or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cordialement
    -0.45
     gedrag
    -0.41
    ponses
    -0.40
    PhysRev
    -0.40
     waard
    -0.40
     عنها
    -0.38
     miliardi
    -0.36
    ucus
    -0.36
    ey
    -0.35
     Kluwer
    -0.35
    POSITIVE LOGITS
     install
    3.67
     installation
    3.50
     Install
    3.39
    Install
    3.30
    install
    3.30
     installing
    3.28
     Installation
    3.25
     installs
    3.17
     installed
    3.11
    Installation
    3.06
    Activations Density 0.127%

    No Known Activations