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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1202
    Prev
    Next
    INDEX
    Explanations

    attends to closing parentheses tokens from opening curly brace tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.03
    1:0.01
    2:0.00
    3:0.01
    4:0.01
    5:0.00
    6:0.02
    7:0.04
    8:0.68
    9:0.02
    10:0.01
    11:0.01
    12:0.01
    13:0.02
    14:0.01
    15:0.02
    Negative Logits
     civilización
    -0.40
     perfección
    -0.40
     pierna
    -0.38
     Económica
    -0.36
     almohada
    -0.36
     totalidad
    -0.35
     zijne
    -0.35
     herida
    -0.34
     nocturno
    -0.34
     plegable
    -0.34
    POSITIVE LOGITS
     ویکی‌پدی
    1.02
    
    0.92
    
    0.90
    
    0.88
    uxxxx
    0.87
    
    0.86
    
    0.86
    𓆱
    0.86
    𖡻
    0.85
    
    0.85
    Activations Density 1.509%

    No Known Activations