© 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. 28-GEMMASCOPE-RES-16K
    11. 4671
    Prev
    Next
    INDEX
    Explanations

    snippets of code that involve function or method definitions

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

    Coordinates, positions, or locations

    np_acts-logits-general · gemini-2.0-flash

    point coordinates and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.69
    providedIn
    -0.59
    
    -0.50
     CommonModule
    -0.50
     AssemblyCompany
    -0.49
     BrowserModule
    -0.43
    AutoScaleMode
    -0.42
    panes
    -0.42
     complémentaires
    -0.41
    explique
    -0.41
    POSITIVE LOGITS
     location
    1.23
     coordinates
    1.13
     position
    1.09
     locations
    1.08
     Location
    1.00
     point
    0.96
     positions
    0.96
     ubicación
    0.95
     위치
    0.94
    location
    0.93
    Activations Density 0.781%

    No Known Activations