© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 49362
    Prev
    Next
    INDEX
    Explanations

    instructions related to navigating or scrolling through content

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

    scrolling down or to bottom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -0.49
     kasarigan
    -0.49
     setCode
    -0.45
    balleur
    -0.44
     {[
    -0.44
     newNode
    -0.43
     Pax
    -0.40
    htbp
    -0.40
    ʁ
    -0.39
    UnitTesting
    -0.38
    POSITIVE LOGITS
    ChildScrollView
    1.16
     desmotivaciones
    0.71
     scroll
    0.65
    ScrollView
    0.63
    scroll
    0.59
     scrolling
    0.59
    scrolling
    0.59
    SCROLL
    0.54
     scrolls
    0.53
    croll
    0.50
    Activations Density 0.009%

    No Known Activations