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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1174
    Prev
    Next
    INDEX
    Explanations

    attends to mathematical operations or computations marked by special symbols from results or expressions that follow them

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.04
    1:0.03
    2:0.01
    3:0.02
    4:0.01
    5:0.01
    6:0.39
    7:0.09
    8:0.03
    9:0.03
    10:0.04
    11:0.02
    12:0.04
    13:0.03
    14:0.03
    15:0.10
    Negative Logits
    ]))
    -0.52
    ))),
    -0.51
    "))
    -0.50
    }")
    -0.50
    }))
    -0.50
    }},
    -0.50
    )))
    -0.49
    }})
    -0.49
    ))
    -0.48
    ")))
    -0.48
    POSITIVE LOGITS
     queſta
    0.59
     AssemblyCompany
    0.58
    MLLoader
    0.55
    setVerticalGroup
    0.54
    CloseOperation
    0.54
    SBATCH
    0.53
     AssemblyTitle
    0.50
     myſelf
    0.50
    TagMode
    0.50
     Conſ
    0.50
    Activations Density 0.187%

    No Known Activations