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. 465
    Prev
    Next
    INDEX
    Explanations

    attends to the token "En" from tokens related to "thalpy."

    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
    0:0.06
    1:0.03
    2:0.05
    3:0.05
    4:0.08
    5:0.56
    6:0.09
    7:0.04
    Negative Logits
     quæ
    -0.33
     espirituales
    -0.29
     cív
    -0.29
     tuyo
    -0.29
    _
    -0.28
     Tampoco
    -0.27
     Jurí
    -0.27
     alpina
    -0.27
    RegressionTest
    -0.27
     ejus
    -0.27
    POSITIVE LOGITS
    fromCharCode
    0.34
    GraphicsUnit
    0.33
    invokeLater
    0.33
    Personendaten
    0.32
    Архівовано
    0.31
     >=",
    0.30
    存于互联网档案馆
    0.29
    期刊论文
    0.29
    openzeppelin
    0.29
    afficheront
    0.28
    Activations Density 0.013%

    No Known Activations