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. 1230
    Prev
    Next
    INDEX
    Explanations

    attends to comment markers from software-related 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
    0:0.05
    1:0.04
    2:0.00
    3:0.02
    4:0.02
    5:0.05
    6:0.03
    7:0.04
    8:0.31
    9:0.11
    10:0.07
    11:0.03
    12:0.04
    13:0.02
    14:0.01
    15:0.06
    Negative Logits
     $_(
    -0.53
    хьтан
    -0.52
    ſelf
    -0.51
    expandindo
    -0.48
     queſta
    -0.47
    
    -0.46
    ंदीखरीदारी
    -0.46
    :✨
    -0.46
     disambiguazione
    -0.46
    ſelves
    -0.45
    POSITIVE LOGITS
    *
    0.35
     *
    0.31
    ↵
    0.31
     //
    0.28
    ↵↵
    0.27
    //
    0.27
    /*
    0.26
    /**
    0.24
     I
    0.24
     A
    0.24
    Activations Density 0.270%

    No Known Activations