© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 65435
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or names related to tables, patients, and other detailed records

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

    designation or named entities

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     adelante
    -0.43
     dezelve
    -0.40
     grounded
    -0.39
     cumplido
    -0.38
     formó
    -0.36
     Bourgeois
    -0.35
     entregado
    -0.35
     gustado
    -0.34
     ayudado
    -0.34
    Điều
    -0.34
    POSITIVE LOGITS
    sizeCache
    0.84
     فريبيس
    0.73
    PerformLayout
    0.66
     NSCoder
    0.65
     utafitiHapana
    0.63
    WriteTagHelper
    0.62
    évaluateur
    0.61
    extAlignment
    0.60
     Normdatei
    0.60
     Infórmanos
    0.60
    Activations Density 0.511%

    No Known Activations