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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39622
    Prev
    Next
    INDEX
    Explanations

    references to specific geometric shapes, particularly those related to technology and engineering

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

    geometric shapes followed by shaped

    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
     behand
    -0.30
     trata
    -0.29
     treated
    -0.29
    ウター
    -0.28
    cional
    -0.28
    ButtonClicked
    -0.28
    dpy
    -0.27
    IMENTAL
    -0.27
     Berlin
    -0.26
     tap
    -0.26
    POSITIVE LOGITS
     HasFactory
    0.78
    tanleria
    0.77
     surla
    0.75
    ScopeManager
    0.74
     ujednoznacz
    0.73
    FormTagHelper
    0.69
    DoubleQuotes
    0.68
    DeleteBehavior
    0.68
    ंदीखरीदारी
    0.68
    shaped
    0.68
    Activations Density 0.056%

    No Known Activations