© 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. 237
    Prev
    Next
    INDEX
    Explanations

    technical terminology and specific product names in scientific contexts

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

    Lab reagents or experimental conditions

    np_acts-logits-general · gemini-2.0-flash

    lab chemicals and procedures

    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
     charakterysty
    -0.41
    Diweddarwch
    -0.41
     initComponents
    -0.39
     שוליים
    -0.38
    ⓧ
    -0.37
     bowiem
    -0.37
    ographia
    -0.36
     rodzic
    -0.36
     conformidad
    -0.36
     AssemblyTitle
    -0.36
    POSITIVE LOGITS
    stateMutability
    0.53
     ब्रेकडाउन
    0.50
     protoimpl
    0.50
     springfox
    0.47
     AssemblyCompany
    0.47
     chip
    0.44
    ftagPool
    0.43
     EClass
    0.43
     Lakeside
    0.43
     royal
    0.42
    Activations Density 0.588%

    No Known Activations