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. 1195
    Prev
    Next
    INDEX
    Explanations

    attends to various forms of "given" from specific token references later in the sequence

    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
    0:0.00
    1:0.00
    2:0.55
    3:0.01
    4:0.00
    5:0.00
    6:0.13
    7:0.06
    8:0.00
    9:0.00
    10:0.00
    11:0.00
    12:0.00
    13:0.06
    14:0.08
    15:0.00
    Negative Logits
     the
    -0.51
     effect
    -0.46
     one
    -0.44
     year
    -0.42
     end
    -0.40
     order
    -0.40
     two
    -0.40
     chapter
    -0.40
     day
    -0.39
     list
    -0.39
    POSITIVE LOGITS
     zijne
    0.56
     asesinado
    0.56
     mijne
    0.51
     Komunikasi
    0.51
     onderhoud
    0.50
     leerlingen
    0.50
     bezoekers
    0.50
     Kebijakan
    0.49
    IsMutable
    0.49
     herido
    0.49
    Activations Density 0.095%

    No Known Activations