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. 309
    Prev
    Next
    INDEX
    Explanations

    attends to "cars" from various related tokens appearing later in the sequence

    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
    0:0.73
    1:0.01
    2:0.01
    3:0.03
    4:0.11
    5:0.03
    6:0.01
    7:0.03
    Negative Logits
    Autoritní
    -0.36
     мәкал
    -0.35
    первых
    -0.33
     LEYENDO
    -0.33
     resourceCulture
    -0.33
     autorytatywna
    -0.33
    Hentet
    -0.31
    ทุน
    -0.31
    )*/
    -0.31
     Wikimédia
    -0.30
    POSITIVE LOGITS
    jsonwebtoken
    0.30
    ReadLine
    0.28
    usão
    0.23
    atisk
    0.22
     verste
    0.22
    ituary
    0.21
    âmica
    0.21
    ’
    0.21
     tari
    0.21
     उनकी
    0.21
    Activations Density 0.031%

    No Known Activations