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. 383
    Prev
    Next
    INDEX
    Explanations

    attends to "follow" in the context of various tokens relating to the continuation or readership of content from earlier 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
    0:0.51
    1:0.01
    2:0.03
    3:0.02
    4:0.20
    5:0.08
    6:0.02
    7:0.09
    Negative Logits
    原始内容存档于
    -0.56
     cherchés
    -0.54
    ThroughAttribute
    -0.53
    ImageContext
    -0.53
     referenties
    -0.52
     дописавши
    -0.52
    XMLSchema
    -0.49
    Enllaces
    -0.48
    cookieParser
    -0.48
    GEBURTSDATUM
    -0.47
    POSITIVE LOGITS
     credere
    0.38
     morire
    0.37
     vapa
    0.36
     sportivo
    0.36
     elä
    0.35
     kılıf
    0.34
     Majefty
    0.34
     esterno
    0.34
     subsoil
    0.33
     valmist
    0.33
    Activations Density 0.042%

    No Known Activations