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. 10-GEMMASCOPE-ATT-16K
    6. 6014
    Prev
    Next
    INDEX
    Explanations

    attends to the opening parentheses of citations from the closing parentheses of the same citations

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.19
    1:0.14
    2:0.29
    3:0.05
    4:0.07
    5:0.10
    6:0.06
    7:0.06
    Negative Logits
    SupportActionBar
    -0.35
     setUsername
    -0.29
    Tembelea
    -0.29
     ostavi
    -0.28
    êcher
    -0.28
     BufferedWriter
    -0.28
    alamualaikum
    -0.27
    gründ
    -0.27
     JSONException
    -0.27
    ResumeLayout
    -0.27
    POSITIVE LOGITS
    LookAnd
    0.39
     فريبيس
    0.37
    లాలు
    0.33
     Geschichts
    0.33
    таратура
    0.32
     mergeFrom
    0.32
     Hift
    0.32
    IUrlHelper
    0.32
    inquirer
    0.32
    SharedCtor
    0.31
    Activations Density 0.128%

    No Known Activations