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. 225
    Prev
    Next
    INDEX
    Explanations

    attends to comment tokens marked as " //" from various other tokens

    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
    0:0.01
    1:0.68
    2:0.02
    3:0.01
    4:0.03
    5:0.13
    6:0.03
    7:0.04
    Negative Logits
    //
    -0.65
    TagMode
    -0.57
    /*
    -0.55
     //
    -0.50
     الحره
    -0.49
    +#+#
    -0.48
     /*
    -0.47
    /*---
    -0.45
    batore
    -0.44
    /**
    -0.44
    POSITIVE LOGITS
    veste
    0.35
    AccessException
    0.35
    DebuggerStep
    0.35
    IANI
    0.34
    ÁT
    0.34
     trône
    0.33
    少
    0.33
    ICATION
    0.33
     they
    0.33
     пара
    0.33
    Activations Density 0.046%

    No Known Activations