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. 6511
    Prev
    Next
    INDEX
    Explanations

    attends to tokens indicating social media or sharing from contexts involving sharing information or content

    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
    0:0.10
    1:0.16
    2:0.17
    3:0.08
    4:0.10
    5:0.07
    6:0.08
    7:0.21
    Negative Logits
    endphp
    -0.35
     "..\..\
    -0.25
     Перейти
    -0.25
    허
    -0.24
    棄
    -0.24
     fastest
    -0.23
     vendar
    -0.23
    Cited
    -0.23
    MVH
    -0.23
     quickest
    -0.22
    POSITIVE LOGITS
     autorytatywna
    0.44
     Roskov
    0.38
    AnimationsModule
    0.36
    contentLoaded
    0.35
    دانشنامهٔ
    0.34
    Autoritní
    0.34
    __":
    
    0.32
    Personensuche
    0.31
    Välislingid
    0.31
    Composable
    0.30
    Activations Density 0.008%

    No Known Activations