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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5717
    Prev
    Next
    INDEX
    Explanations

    attends to general abilities or states from specific actions or conditions that follow

    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
    0:0.09
    1:0.10
    2:0.10
    3:0.16
    4:0.14
    5:0.05
    6:0.16
    7:0.17
    Negative Logits
     HasFactory
    -0.35
     StyleSheet
    -0.34
    قایناقلار
    -0.34
    Tembelea
    -0.33
    Personendaten
    -0.32
    Tikang
    -0.31
    IonicModule
    -0.31
    WebElementEntity
    -0.31
     مشين
    -0.30
     Winaray
    -0.30
    POSITIVE LOGITS
    ASTE
    0.24
    conomie
    0.23
    nitive
    0.23
    korn
    0.23
    UNCH
    0.23
    coming
    0.23
    =*/
    0.23
    uza
    0.22
    isburg
    0.22
    oton
    0.21
    Activations Density 0.155%

    No Known Activations