Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6655
    Prev
    Next
    INDEX
    Explanations

    attends to tokens that are marked with asterisks, indicating a focus on certain highlighted variables or terms from surrounding tokens that are in brackets

    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
    0:0.03
    1:0.06
    2:0.04
    3:0.03
    4:0.22
    5:0.52
    6:0.03
    7:0.03
    Negative Logits
    unesse
    -0.23
     prés
    -0.20
    {{\
    -0.20
    EndTag
    -0.20
    mybatisplus
    -0.20
    diğini
    -0.19
     BrowserRouter
    -0.19
     Judge
    -0.19
     -
    -0.19
     disambiguazione
    -0.19
    POSITIVE LOGITS
    Cyfeiriadau
    0.43
    \{\\
    0.38
    Билгалдахарш
    0.37
     gyhoeddwyd
    0.37
     насеље
    0.36
    XmlAccessType
    0.36
    Demografie
    0.35
     kasarigan
    0.33
     externi
    0.33
    🏾
    0.33
    Activations Density 1.234%

    No Known Activations