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. 1315
    Prev
    Next
    INDEX
    Explanations

    attends to section-related tokens from subsections and clauses

    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
    0:0.04
    1:0.03
    2:0.00
    3:0.02
    4:0.01
    5:0.04
    6:0.02
    7:0.02
    8:0.07
    9:0.51
    10:0.05
    11:0.03
    12:0.03
    13:0.02
    14:0.00
    15:0.02
    Negative Logits
     Italij
    -0.60
     miniaturka
    -0.57
     desmotivaciones
    -0.57
     plegable
    -0.56
     zijne
    -0.54
     orgánico
    -0.54
     avoient
    -0.54
     Económica
    -0.54
     Inscrivez
    -0.53
     Infór
    -0.52
    POSITIVE LOGITS
    ,
    0.66
    -
    0.59
     Mi
    0.59
     Ag
    0.59
     
    0.58
     Tri
    0.58
     Tr
    0.57
     Ri
    0.57
     T
    0.57
     Cam
    0.57
    Activations Density 0.539%

    No Known Activations