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. 5788
    Prev
    Next
    INDEX
    Explanations

    attends to numerical values that are separated by commas from numerical values that follow 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
    0:0.13
    1:0.17
    2:0.10
    3:0.07
    4:0.14
    5:0.04
    6:0.06
    7:0.24
    Negative Logits
     snippetHide
    -0.38
     للمعارف
    -0.35
     للاسماء
    -0.35
    ftagPool
    -0.34
    IsPostBack
    -0.33
    ########.
    -0.31
    cessite
    -0.30
     lenker
    -0.30
    expandindo
    -0.30
     Италијани
    -0.29
    POSITIVE LOGITS
     ujednoznacz
    0.36
    interopRequire
    0.28
    (__('
    0.27
    __("
    0.27
    ので
    0.26
    存于互联网档案馆
    0.26
    XmlAccessType
    0.25
    ReusableCell
    0.25
    andre
    0.25
    Slf
    0.25
    Activations Density 0.572%

    No Known Activations