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. 0-GEMMASCOPE-ATT-16K
    6. 6104
    Prev
    Next
    INDEX
    Explanations

    attends to the token "Exception" from token identifiers or labels that indicate specific context

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 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
    0:0.01
    1:0.02
    2:0.05
    3:0.51
    4:0.05
    5:0.04
    6:0.13
    7:0.14
    Negative Logits
    lader
    -0.34
    ]}>
    -0.33
    ]$}
    -0.32
    postcss
    -0.32
    resizingMask
    -0.31
    :]:
    -0.30
    ILON
    -0.30
    StandardCharsets
    -0.30
    ]};
    -0.30
    ExecuteReader
    -0.29
    POSITIVE LOGITS
     industriels
    0.40
     énergé
    0.40
     russes
    0.39
     africains
    0.39
     réguli
    0.38
     fédé
    0.38
     actuels
    0.37
     religieuses
    0.36
     suivants
    0.36
     giuri
    0.36
    Activations Density 0.408%

    No Known Activations