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. 40
    Prev
    Next
    INDEX
    Explanations

    attends to the action of appending from the context of a data structure or collection to a secondary resource or format

    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
    0:0.01
    1:0.03
    2:0.08
    3:0.30
    4:0.06
    5:0.07
    6:0.22
    7:0.20
    Negative Logits
    abestanden
    -0.47
    setVerticalGroup
    -0.46
     CreateTagHelper
    -0.42
    — 
    -0.41
    AddTagHelper
    -0.40
    ratulations
    -0.40
    ')):
    -0.40
     bag
    -0.39
    BibitemShut
    -0.38
     GenerationType
    -0.37
    POSITIVE LOGITS
     feroit
    0.68
     avoient
    0.67
     auroit
    0.63
     spirituale
    0.62
     étoit
    0.60
     étoient
    0.60
     titolata
    0.60
     réguli
    0.60
     quæ
    0.59
     vocale
    0.59
    Activations Density 0.116%

    No Known Activations