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. 6403
    Prev
    Next
    INDEX
    Explanations

    attends to terms related to government or organizational structures from specifications of what these structures pertain to in context

    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
    0:0.15
    1:0.31
    2:0.11
    3:0.06
    4:0.12
    5:0.05
    6:0.05
    7:0.10
    Negative Logits
    ViewImports
    -0.49
     numberOfRows
    -0.48
    sidemargin
    -0.45
    setVerticalGroup
    -0.45
    তথ্যসূত্র
    -0.42
    حوالہ
    -0.41
     Theſe
    -0.39
     CreateTagHelper
    -0.39
     purpoſe
    -0.39
     bezeichneter
    -0.38
    POSITIVE LOGITS
     "..\..\
    0.26
    чу
    0.25
     earlier
    0.25
     later
    0.24
     few
    0.24
    :
    0.23
     :
    0.23
    ulihan
    0.23
     miatt
    0.22
    ut
    0.22
    Activations Density 0.406%

    No Known Activations