© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 68
    Prev
    Next
    INDEX
    Explanations

    programming code related to file management operations

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

    Code snippets ending in parentheses/semicolons

    np_acts-logits-general · gemini-2.0-flash

    path get depth

    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
    Chham
    -0.60
     للاسماء
    -0.57
    AndEndTag
    -0.56
    ConstraintMaker
    -0.56
     CreateTagHelper
    -0.50
    Oneof
    -0.45
     насељу
    -0.44
    RTLU
    -0.44
     Administrativna
    -0.44
    Tembelea
    -0.44
    POSITIVE LOGITS
    WaitGroup
    0.44
    >{@
    0.37
    Solids
    0.36
    endwhile
    0.33
    istoitu
    0.33
     meren
    0.33
    MemoryWarning
    0.33
    prisma
    0.32
     autorytatywna
    0.32
    Kaynakça
    0.32
    Activations Density 0.102%

    No Known Activations