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. 5563
    Prev
    Next
    INDEX
    Explanations

    attends to pairs of tokens that involve multiple uses of brackets from tokens later in the sequence

    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
    0:0.22
    1:0.11
    2:0.23
    3:0.10
    4:0.10
    5:0.05
    6:0.07
    7:0.09
    Negative Logits
    Portail
    -0.28
    }}}{\
    -0.27
    árl
    -0.25
    }))
    
    -0.25
     plot
    -0.24
    </sub>
    -0.24
     Plots
    -0.23
    '||
    -0.23
    endaftaran
    -0.23
     plots
    -0.23
    POSITIVE LOGITS
    twimg
    0.49
    Geplaatst
    0.42
     ویکی‌پدیا
    0.40
     useAppContext
    0.38
    AddTagHelper
    0.37
    AlterField
    0.36
     Normdatei
    0.35
     myſelf
    0.35
    webElementXpaths
    0.34
     فريبيس
    0.34
    Activations Density 0.001%

    No Known Activations