© 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. 16300
    Prev
    Next
    INDEX
    Explanations

    references to database schema, particularly related to fields and SQL commands

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

    Code diff additions

    np_acts-logits-general · gemini-2.0-flash

    adding or altering fields

    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
    invokeLater
    -0.64
     Administrativna
    -0.61
     Мексичка
    -0.60
    Xna
    -0.56
     jsPsych
    -0.53
    encodeWith
    -0.52
     getItemId
    -0.52
    íqu
    -0.51
    AutoScaleMode
    -0.51
    aarrggbb
    -0.51
    POSITIVE LOGITS
    CreateModel
    0.50
     חיצוניים
    0.45
    AlterField
    0.43
    
    0.38
     scra
    0.38
    Välislingid
    0.36
    AddColumn
    0.36
    AddField
    0.35
    せっかく
    0.35
     consultato
    0.35
    Activations Density 0.029%

    No Known Activations