© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7823
    Prev
    Next
    INDEX
    Explanations

    references to the word "red" and its variations in various contexts

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

    "Red" and its variations

    np_acts-logits-general · gemini-2.0-flash

    Red as a descriptor or part of names

    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
     AssemblyCompany
    -0.64
     CreateTagHelper
    -0.59
    IntoConstraints
    -0.53
     MaterialApp
    -0.50
    Aholisi
    -0.43
     Administrativna
    -0.43
    umented
    -0.43
    fitrión
    -0.42
    lovakia
    -0.42
    plink
    -0.42
    POSITIVE LOGITS
     Red
    0.93
     RED
    0.87
    Red
    0.81
     red
    0.77
     红
    0.67
     レッド
    0.63
     reds
    0.63
     Reds
    0.61
     Redmond
    0.61
     Rede
    0.60
    Activations Density 0.122%

    No Known Activations