© 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. 18-GEMMASCOPE-RES-16K
    11. 11682
    Prev
    Next
    INDEX
    Explanations

    key phrases and terms associated with projects and initiatives in defense and public works

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

    "project" or "projects"

    np_acts-logits-general · gemini-2.0-flash

    project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.68
     pinulongan
    -0.65
    ThroughAttribute
    -0.60
    XmlAccessType
    -0.60
    OGND
    -0.58
    Geplaatst
    -0.58
     estekak
    -0.57
    évaluateur
    -0.57
    UrlResolution
    -0.56
    Personensuche
    -0.56
    POSITIVE LOGITS
     project
    2.95
     projects
    2.66
    project
    2.54
     Project
    2.35
    Project
    2.31
    projects
    2.30
     proyecto
    2.25
     projet
    2.25
     Projects
    2.18
     PROJECT
    2.15
    Activations Density 0.294%

    No Known Activations