© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2472
    Prev
    Next
    INDEX
    Explanations

    occurrences of the color "red" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.41
     BrowserModule
    -0.39
     EFT
    -0.38
     
    -0.37
    ModelForm
    -0.35
     corso
    -0.35
    ikea
    -0.35
     MaterialApp
    -0.35
    🥒
    -0.35
     Signalez
    -0.34
    POSITIVE LOGITS
     red
    3.08
     Red
    2.98
    Red
    2.88
     RED
    2.81
    red
    2.73
    RED
    2.69
     reds
    2.30
    红
    2.25
    紅
    2.14
     Reds
    2.09
    Activations Density 0.233%

    No Known Activations