© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10247
    Prev
    Next
    INDEX
    Explanations

    terms related to prefixes and suffixes in programming and markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    __":
    -0.67
    __':
    -0.63
    __':
    
    -0.56
     "..\..\..\
    -0.54
    {
    
    
    -0.54
    __":
    
    -0.54
    存于互联网档案馆
    -0.52
    ContentAsync
    -0.52
    PYX
    -0.51
     >(
    -0.48
    POSITIVE LOGITS
     tag
    0.84
     Prefix
    0.70
    Prefix
    0.69
     prefix
    0.69
    tag
    0.67
     tagName
    0.65
     suffix
    0.65
     etiqueta
    0.65
    prefix
    0.64
     tags
    0.64
    Activations Density 0.263%

    No Known Activations