© 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. 1717
    Prev
    Next
    INDEX
    Explanations

    closing braces and specific syntactic structures in code

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

    Code snippets with "return false"

    np_acts-logits-general · gemini-2.0-flash

    html/xml structure closing tags

    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
     surla
    -0.87
     nahilalakip
    -0.86
    AddTagHelper
    -0.84
     betweenstory
    -0.84
    Personendaten
    -0.81
    
    -0.79
    WebVitals
    -0.79
    __":
    
    -0.78
    __':
    
    -0.76
    MessageOf
    -0.75
    POSITIVE LOGITS
    .
    0.51
    <eos>
    0.47
    ↵↵
    0.44
    Volver
    0.36
    ↵
    0.36
     .
    0.35
    1
    0.35
     Weiner
    0.35
     sk
    0.35
     Honig
    0.35
    Activations Density 0.122%

    No Known Activations