© 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. 15716
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to functions and transformations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Mathematical or programming-related symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation delimiters

    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
    Negative Logits
     him
    -0.61
    Mr
    -0.60
     Mr
    -0.58
     he
    -0.52
    老公
    -0.50
    看着他
    -0.50
    |}{$
    -0.49
     het
    -0.49
    iseerd
    -0.49
    esus
    -0.48
    POSITIVE LOGITS
     Ms
    0.79
     della
    0.71
     της
    0.67
    ńskiej
    0.65
    Ms
    0.65
    jącej
    0.63
    tagHelper
    0.62
     ladite
    0.57
    ".$_
    0.57
     takiej
    0.57
    Activations Density 2.314%

    No Known Activations