Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3265
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and technical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.10
    '}>
    -1.09
     XNUMX
    -1.01
    '])){
    
    -0.94
    '){
    
    -0.91
    ousand
    -0.91
    parsedMessage
    -0.91
    endence
    -0.90
    "){
    
    -0.88
    Rhestr
    -0.87
    POSITIVE LOGITS
     Champs
    0.93
    httphttps
    0.85
     Bucs
    0.83
     Atty
    0.80
    QUADS
    0.77
     meds
    0.76
     تانيه
    0.75
    Eqn
    0.74
     GONNA
    0.73
     Pollut
    0.73
    Activations Density 0.748%

    No Known Activations