© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9247
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

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

    Mathematical expressions or code snippets

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and code

    np_acts-logits-general · gemini-2.5-flash-lite

    symbolic math expressions and problem statements involving variables, exponents, arithmetic operations on fractions, and queries about divisibility, comparison, or simplification.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     CreateTagHelper
    -0.77
     سكانية
    -0.69
     autorytatywna
    -0.67
     Infórmanos
    -0.66
    principalColumn
    -0.65
     виправивши
    -0.64
     BorderSide
    -0.63
    UnitTesting
    -0.63
    UnusedPrivate
    -0.63
    disposing
    -0.62
    POSITIVE LOGITS
     compañ
    0.33
    Rohy
    0.33
     متحده
    0.30
     tibur
    0.28
    Derbyniad
    0.28
     للاسماء
    0.26
     vẻ
    0.24
    &#
    0.24
    ...
    0.24
     forne
    0.24
    Activations Density 13.306%

    No Known Activations