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. 5897
    Prev
    Next
    INDEX
    Explanations

    attends to clothing-related tokens from accessory-related tokens

    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
    0:0.16
    1:0.23
    2:0.13
    3:0.07
    4:0.10
    5:0.03
    6:0.06
    7:0.18
    Negative Logits
    IntoConstraints
    -0.31
    AutoSize
    -0.28
    InputTagHelper
    -0.27
     BoxDecoration
    -0.26
     jadi
    -0.24
     ngang
    -0.24
    tipation
    -0.24
    τως
    -0.24
    Хьажоргаш
    -0.24
    SourceChecksum
    -0.23
    POSITIVE LOGITS
    lup
    0.31
     tirage
    0.29
     userRepository
    0.28
     âme
    0.28
     GetUser
    0.27
    Бахар
    0.27
    ganu
    0.27
    ubis
    0.27
     encou
    0.27
    IMPORTED
    0.27
    Activations Density 0.138%

    No Known Activations