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. 6578
    Prev
    Next
    INDEX
    Explanations

    attends to the functions and actions related to user interaction from elements that detail descriptions or properties associated with those actions

    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
    0:0.07
    1:0.10
    2:0.06
    3:0.47
    4:0.11
    5:0.03
    6:0.05
    7:0.07
    Negative Logits
    TypedDataSet
    -0.56
    PreferredItem
    -0.53
    ItemBackground
    -0.50
    InitVars
    -0.49
     actionMode
    -0.48
    +#+#
    -0.47
    Климат
    -0.47
     apellidos
    -0.45
    tikzpicture
    -0.43
     '\\;'
    -0.43
    POSITIVE LOGITS
     ujednoznacz
    0.63
    MockMvc
    0.53
    ViewImports
    0.48
    tvguidetime
    0.42
     kysy
    0.40
     forcé
    0.39
     affitto
    0.38
    MockBean
    0.38
    ]>
    0.38
     crossorigin
    0.38
    Activations Density 1.169%

    No Known Activations