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. 0-GEMMASCOPE-ATT-16K
    6. 6074
    Prev
    Next
    INDEX
    Explanations

    attends from mathematical token patterns to their respective labeled categories

    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
    0:0.07
    1:0.02
    2:0.03
    3:0.04
    4:0.64
    5:0.08
    6:0.06
    7:0.04
    Negative Logits
    ↵
    -0.33
        
    -0.33
     onOptions
    -0.32
       
    -0.32
     communis
    -0.32
    [
    -0.32
    1
    -0.31
                                   
    -0.31
    </em>
    -0.30
     zis
    -0.30
    POSITIVE LOGITS
    tvguidetime
    0.70
    $.
    
    0.63
    IntoConstraints
    0.63
     ]
    
    0.62
    脚注の使い方
    0.58
     Paglinawan
    0.56
    RegressionTest
    0.56
     autorytatywna
    0.52
    EndGlobalSection
    0.52
    ^(@)
    0.52
    Activations Density 0.172%

    No Known Activations