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. 5754
    Prev
    Next
    INDEX
    Explanations

    attends to UISlider properties marked by the token "UISlider" from the token "selector" as well as related actions from subsequent tokens

    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
    0:0.10
    1:0.19
    2:0.05
    3:0.04
    4:0.09
    5:0.42
    6:0.03
    7:0.04
    Negative Logits
    OGND
    -0.31
    complexType
    -0.27
    BindingResult
    -0.26
     Kome
    -0.26
    enumi
    -0.25
    jamientos
    -0.25
    makeConstraints
    -0.24
    ništvo
    -0.24
    elasticsearch
    -0.23
     <<<<<<<<<<<<<<
    -0.23
    POSITIVE LOGITS
     respectivement
    0.26
     âgé
    0.26
     continúas
    0.26
     rheinland
    0.25
    Filmographie
    0.25
     adultes
    0.25
     plong
    0.24
     récon
    0.24
     fraî
    0.24
    gars
    0.24
    Activations Density 0.035%

    No Known Activations