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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16217
    Prev
    Next
    INDEX
    Explanations

    references to legal doctrines and procedures in judicial contexts

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

    that can precede a statement

    np_acts-logits-general · gemini-2.0-flash

    discussing rules and concepts

    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
    verwijspagina
    -0.83
     queſta
    -0.82
     Италијани
    -0.75
    ChildScrollView
    -0.75
    windowFixed
    -0.74
    parsedMessage
    -0.71
    Tikang
    -0.71
     Administrativna
    -0.70
     utafitiHapana
    -0.70
     otomatig
    -0.69
    POSITIVE LOGITS
     (
    0.33
    vir
    0.32
    行
    0.30
     limited
    0.30
     ever
    0.30
     pretty
    0.30
     corregir
    0.30
     voie
    0.29
    启
    0.29
    proto
    0.28
    Activations Density 1.315%

    No Known Activations