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. 6043
    Prev
    Next
    INDEX
    Explanations

    attends to the structure or type indicators associated with specified functions or categories from arithmetic or programmatic terms

    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
    0:0.13
    1:0.11
    2:0.13
    3:0.08
    4:0.07
    5:0.03
    6:0.07
    7:0.34
    Negative Logits
    帖最后由
    -0.30
     even
    -0.27
     szóci
    -0.26
     ge
    -0.26
    ürger
    -0.26
     rather
    -0.25
    getBoolean
    -0.25
     Adler
    -0.25
    degard
    -0.24
     vege
    -0.24
    POSITIVE LOGITS
    errHandler
    0.42
    ConstraintMaker
    0.39
    titleMargin
    0.38
    :✨
    0.38
     للمعارف
    0.37
    sidenav
    0.37
    addCriterion
    0.36
     Paglinawan
    0.35
    ContentAsync
    0.35
     kasarigan
    0.35
    Activations Density 2.101%

    No Known Activations