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. 70
    Prev
    Next
    INDEX
    Explanations

    attends to the token "project" from the token "was" or other related verbs that indicate its status or actions

    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
    2:0.17
    3:0.38
    4:0.06
    5:0.04
    6:0.15
    7:0.12
    Negative Logits
     AssemblyTitle
    -0.32
    Scénario
    -0.30
     onCreateView
    -0.29
     pleaſure
    -0.29
    неопр
    -0.29
     Şi
    -0.29
     becauſe
    -0.29
     auffi
    -0.28
    IntoConstraints
    -0.28
     Monfieur
    -0.28
    POSITIVE LOGITS
     Projects
    0.46
     projects
    0.46
    Projects
    0.45
    projects
    0.45
    ]));
    
    0.43
     PROJECTS
    0.41
     progetti
    0.40
     projets
    0.39
     project
    0.39
     Projekte
    0.39
    Activations Density 1.441%

    No Known Activations