© 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. 30-GEMMASCOPE-RES-16K
    11. 12489
    Prev
    Next
    INDEX
    Explanations

    color descriptions and their associations in various contexts

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

    Colors (blue, red, green, orange)

    np_acts-logits-general · gemini-2.0-flash

    list of colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    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
    -0.73
     autorytatywna
    -0.67
    OGND
    -0.60
    DockStyle
    -0.59
     viewDidLoad
    -0.58
    
    -0.57
    +#+
    -0.56
     CreateTagHelper
    -0.54
    fromnode
    -0.54
    enterOuterAlt
    -0.53
    POSITIVE LOGITS
     white
    1.53
     yellow
    1.40
     blue
    1.36
     black
    1.33
     green
    1.26
    white
    1.20
     gray
    1.17
     red
    1.16
     orange
    1.14
     purple
    1.14
    Activations Density 0.304%

    No Known Activations