© 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. 28-GEMMASCOPE-RES-16K
    11. 1194
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas involving fractions

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

    Mathematical symbols within equations

    np_acts-logits-general · gemini-2.0-flash

    greek letters and mathematical notation

    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
    Negative Logits
     queſta
    -0.82
    ChildScrollView
    -0.77
    AutoField
    -0.74
    oa̍t
    -0.73
    ſſung
    -0.73
    FormTagHelper
    -0.71
    ロウィン
    -0.70
     betweenstory
    -0.69
     unſer
    -0.69
    ſelben
    -0.69
    POSITIVE LOGITS
    }{
    0.62
     }{
    0.40
    }{\
    0.36
     recevrez
    0.33
     presidencial
    0.32
     barriga
    0.31
    }}{
    0.31
    </h2>
    0.30
     yoksa
    0.29
    </strong>
    0.29
    Activations Density 0.803%

    No Known Activations