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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-ATT-16K
    6. 6467
    Prev
    Next
    INDEX
    Explanations

    attends to numerical tokens appearing later in the sequence from mathematical notation or abstract concepts appearing earlier

    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
    0:0.03
    1:0.06
    2:0.04
    3:0.04
    4:0.14
    5:0.59
    6:0.03
    7:0.04
    Negative Logits
     NSCoder
    -0.40
    ScopeManager
    -0.39
    
    -0.35
    IntentFilter
    -0.35
     MessageBoxIcon
    -0.31
     newBuilder
    -0.30
    yntaxException
    -0.30
     betweenstory
    -0.30
     esterni
    -0.29
     Abp
    -0.29
    POSITIVE LOGITS
    tvguidetime
    0.27
     brancas
    0.22
     تانيه
    0.20
    omentos
    0.18
     parha
    0.18
     Taktlose
    0.18
     continúas
    0.17
     دیگه
    0.17
    velser
    0.17
     nieuws
    0.17
    Activations Density 1.367%

    No Known Activations