© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1367
    Prev
    Next
    INDEX
    Explanations

    references to databases and records management within a technical context

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

    Precedes different prepositions and punctuation

    np_acts-logits-general · gemini-2.0-flash

    specialized vocabulary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -1.04
     noDo
    -0.91
    ьаж
    -0.90
    IndentedString
    -0.85
    EndGlobalSection
    -0.84
    AutoScaleMode
    -0.82
    IUrlHelper
    -0.81
    Personensuche
    -0.79
    msgTypes
    -0.76
    ंदीखरीदारी
    -0.75
    POSITIVE LOGITS
     surla
    0.48
    extAlignment
    0.39
     Вікіпе
    0.38
     fortæ
    0.35
    
    0.35
    ClientRect
    0.33
    Abraços
    0.33
    fastjson
    0.32
     filós
    0.31
     enfermos
    0.30
    Activations Density 42.664%

    No Known Activations