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. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 314
    Prev
    Next
    INDEX
    Explanations

    attends to specific tokens associated with subscription events from subsequent execution commands

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.08
    3:0.47
    4:0.05
    5:0.06
    6:0.15
    7:0.09
    Negative Logits
     Económica
    -0.47
     Inscrivez
    -0.44
     flutes
    -0.41
     Sopho
    -0.40
     Molière
    -0.40
     Ancona
    -0.40
     Monfieur
    -0.39
     Epistle
    -0.39
     Diſ
    -0.38
     Adagio
    -0.38
    POSITIVE LOGITS
    — 
    0.40
    })*/
    0.39
    }{*}{}
    0.38
    ")){
    
    0.38
    "){
    
    0.37
    æa
    0.37
    ++){
    
    0.36
    ullable
    0.36
    ";}
    0.36
    pecially
    0.36
    Activations Density 0.060%

    No Known Activations