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. 1232
    Prev
    Next
    INDEX
    Explanations

    attends to the token "Flags" from the token "Flag."

    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
    0:0.06
    1:0.04
    2:0.01
    3:0.02
    4:0.02
    5:0.01
    6:0.05
    7:0.06
    8:0.02
    9:0.04
    10:0.14
    11:0.28
    12:0.07
    13:0.07
    14:0.03
    15:0.02
    Negative Logits
    gr
    -0.87
    lu
    -0.85
    ip
    -0.85
    lar
    -0.85
    cr
    -0.85
    aw
    -0.85
    ap
    -0.85
    vu
    -0.84
    alo
    -0.84
    cy
    -0.84
    POSITIVE LOGITS
     Italij
    0.56
     enfans
    0.54
     desmotivaciones
    0.48
     Bewußt
    0.45
     fotográfico
    0.44
     infierno
    0.42
     Wikiseite
    0.41
     Económica
    0.41
     finanzas
    0.41
     vlasy
    0.41
    Activations Density 0.086%

    No Known Activations