© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14601
    Prev
    Next
    INDEX
    Explanations

    references to mathematical equations and algebraic expressions

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

    Mathematical or logical expressions in text

    np_acts-logits-general · gemini-2.0-flash

    lineage viruses, expression levels

    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-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
    IntoConstraints
    -1.06
    хьтан
    -0.61
     defaultstate
    -0.61
    setViewportView
    -0.60
     فريبيس
    -0.56
    ]';
    -0.54
    astéro
    -0.51
     linkovi
    -0.50
    ↹
    -0.49
    الحياه
    -0.48
    POSITIVE LOGITS
    Ӕ
    0.43
     brancas
    0.42
    tagHelperRunner
    0.41
    transQ
    0.40
     AssemblyCompany
    0.40
     Italijani
    0.38
    bcryptjs
    0.36
     @"/
    0.34
     fortæ
    0.33
    anglès
    0.33
    Activations Density 22.607%

    No Known Activations