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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-ATT-16K
    6. 6642
    Prev
    Next
    INDEX
    Explanations

    attends to tokens that are marked as class members or methods by another token that appears later in the sequence

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.07
    1:0.09
    2:0.07
    3:0.11
    4:0.12
    5:0.07
    6:0.31
    7:0.13
    Negative Logits
    yntaxException
    -0.58
     ujednoznacz
    -0.57
     MonoBehaviour
    -0.53
     AssemblyTitle
    -0.53
     виправивши
    -0.50
     vPvB
    -0.44
    Gön
    -0.44
     NSCoder
    -0.44
    IContainer
    -0.43
     lenker
    -0.42
    POSITIVE LOGITS
    												
    0.31
                                 
    0.29
    ↵
    0.29
                        
    0.28
                       
    0.28
    o
    0.27
                                   
    0.26
         
    0.26
                         
    0.26
                                
    0.26
    Activations Density 0.760%

    No Known Activations