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. 1246
    Prev
    Next
    INDEX
    Explanations

    attends to date indications from related event tokens

    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
    1:0.01
    2:0.78
    3:0.01
    4:0.01
    5:0.01
    6:0.01
    7:0.02
    8:0.00
    9:0.00
    10:0.00
    11:0.00
    12:0.00
    13:0.01
    14:0.05
    15:0.01
    Negative Logits
     the
    -0.99
     a
    -0.58
     one
    -0.56
     its
    -0.54
     her
    -0.54
     year
    -0.54
     search
    -0.52
     this
    -0.52
     three
    -0.52
     other
    -0.51
    POSITIVE LOGITS
     Komunikasi
    0.40
     orilla
    0.39
     actualidad
    0.39
     Económica
    0.38
    else
    0.36
     siquiera
    0.36
     Garantía
    0.35
     évêque
    0.35
    IsContent
    0.35
     adopción
    0.35
    Activations Density 0.309%

    No Known Activations