© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5771
    Prev
    Next
    INDEX
    Explanations

    references to a specific project or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "project" or "projects"

    np_acts-logits-general · gemini-2.0-flash

    project, projects, projection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uſed
    -0.74
     Constitucional
    -0.71
    antlr
    -0.69
     écl
    -0.68
     réunis
    -0.67
    paravant
    -0.67
     Bä
    -0.66
    ↴
    -0.63
     angekommen
    -0.63
     whoſe
    -0.63
    POSITIVE LOGITS
     projects
    1.60
     Projects
    1.40
     project
    1.39
     PROJECT
    1.30
    PROJECT
    1.29
    projects
    1.28
    Projects
    1.27
     Project
    1.26
     PROJECTS
    1.22
    project
    1.20
    Activations Density 0.065%

    No Known Activations